© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10857
    Prev
    Next
    INDEX
    Explanations

    buffalo wings

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on specific geographic or institutional names (especially place names) and the numbers or codes that accompany them.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Missouri
    0.64
     Kannada
    0.63
    Missouri
    0.59
     Mississippi
    0.59
     Texas
    0.58
     texas
    0.58
     Oregon
    0.57
    })+\
    0.57
     Texans
    0.57
    Texas
    0.56
    POSITIVE LOGITS
     Syracuse
    1.63
     SUNY
    1.54
     Rochester
    1.53
     upstate
    1.51
     Ithaca
    1.49
     Adirond
    1.41
     Schenectady
    1.34
     Tonawanda
    1.31
     Niagara
    1.27
     Albany
    1.26
    Activations Density 0.228%

    No Known Activations