© 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. 13279
    Prev
    Next
    INDEX
    Explanations

    major cities

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

    This neuron fires on mentions of major city names (e.g. “London” and “New York”).

    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
     sağlı
    0.66
    isão
    0.66
     മന്ത്രി
    0.66
     государство
    0.65
    扡
    0.65
    umā
    0.64
    žit
    0.63
    本来
    0.63
     রাজ্য
    0.62
     towns
    0.62
    POSITIVE LOGITS
     metro
    0.74
     metropolitan
    0.72
    奥运
    0.72
    市内
    0.68
     skyline
    0.66
     Chinatown
    0.65
     Shibuya
    0.65
    🗼
    0.65
     Metropolitan
    0.63
     Olympian
    0.63
    Activations Density 0.241%

    No Known Activations