© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily fires on numeric tokens—especially those denoting ages, years, dates, or other digit-based information.

    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
    有不少
    0.74
     LikeLike
    0.66
    ドラマ
    0.65
     יש
    0.64
     ребята
    0.64
    有一些
    0.63
    有
    0.63
    都有
    0.63
    有很多
    0.63
    有多少
    0.63
    POSITIVE LOGITS
     peacefully
    0.94
    Passed
    0.88
     Passed
    0.86
     died
    0.86
     passed
    0.85
     resident
    0.85
    passed
    0.84
     age
    0.81
     falleció
    0.77
     residente
    0.74
    Activations Density 0.094%

    No Known Activations