© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1376
    Prev
    Next
    INDEX
    Explanations

    explainBetaVegaOpus subtitles

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

    The neuron fires on numeric measurements or reference‐style decimal numbers (e.g. floating‐point values and citation volume/page numbers).

    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_24_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
    中は
    0.80
    ুলি
    0.78
    atakse
    0.73
    َم
    0.71
    कील
    0.71
    में
    0.70
     professor
    0.70
    ନ୍ଦ
    0.70
    प
    0.69
     অচেতন
    0.68
    POSITIVE LOGITS
    一句
    0.71
     demok
    0.71
    兼容
    0.71
    datos
    0.66
     SPORTS
    0.66
     статей
    0.66
     gfx
    0.66
     基于
    0.65
    éléments
    0.65
    ურთი
    0.65
    Activations Density 0.000%

    No Known Activations