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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12302
    Prev
    Next
    INDEX
    Explanations

    words and numbers that form sequences

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

    The neuron is primarily activating on numerical tokens and measurements (e.g. ages, durations, percentages, years, and other 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
    :
    0.73
    re
    0.71
    idade
    0.71
    r
    0.70
     perspectivas
    0.68
    งาม
    0.68
    id
    0.68
    ...”
    0.67
     inferior
    0.65
    ות
    0.65
    POSITIVE LOGITS
     ئەو
    0.87
    饉
    0.81
    ِي
    0.78
    ↺
    0.77
     производи
    0.77
    ራት
    0.77
     공연
    0.76
    自転車
    0.75
     الاعزاء
    0.74
     परीक्षाओं
    0.73
    Activations Density 0.000%

    No Known Activations