© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    historical decades and numbers

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

    This neuron activates on four‐digit numeric tokens representing years (dates).

    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
     ۲
    0.48
     ۱۰
    0.48
     Tetapi
    0.46
    ępuje
    0.44
     Đúng
    0.43
     Secara
    0.43
     cocinar
    0.43
     fuera
    0.42
    impulan
    0.41
     Livraison
    0.41
    POSITIVE LOGITS
     sixties
    0.81
     seventies
    0.79
     eighties
    0.68
     fifties
    0.63
    7
    0.62
     Sevent
    0.57
     nineties
    0.57
    6
    0.57
    late
    0.56
     late
    0.55
    Activations Density 0.170%

    No Known Activations