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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12987
    Prev
    Next
    INDEX
    Explanations

    Colorado locations

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

    This neuron activates on numeric tokens or sequences of digits (numbers, phone numbers, percentages, counts).

    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
    StaticHandler
    0.67
     Merseyside
    0.63
    𒌷
    0.62
    🚢
    0.62
     সিলেট
    0.61
    椹
    0.61
    ⛴
    0.59
    衢
    0.58
    usele
    0.58
    𠃍
    0.58
    POSITIVE LOGITS
     Colorado
    2.41
    Colorado
    2.36
     Denver
    2.22
    Denver
    2.14
     Boulder
    2.02
    Boulder
    1.86
     उत्तराखंड
    1.64
     देहरादून
    1.55
     Rockies
    1.45
     Uttarakhand
    1.45
    Activations Density 0.336%

    No Known Activations