Several recent studies have shown that chickens, fish, and humans trained to find a reward in a corner of a rectangular enclosure with distinctive features rely more on the geometry of the enclosure in small enclosures and rely more on the features in large enclosures. Here, these results are modeled using a recent associative model of geometry learning [Miller, N.Y., Shettleworth, S.J., 2007. Learning about environmental geometry: an associative model. J. Exp. Psychol. Anim. B 33, 191-212]. By adjusting the salience of either geometric or featural information or both the model is capable of reproducing much of the data on the effects of enclosure size on geometry learning.