© 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. 10660
    Prev
    Next
    INDEX
    Explanations

    lists of services

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

    The neuron is selectively activating on numeric tokens—especially section/chapter numbers, volume/page citations, and other standalone 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
     cajas
    0.81
    ivat
    0.75
     Dost
    0.75
    coordinates
    0.74
    gart
    0.73
    含む
    0.72
    )}^{\
    0.70
    ペース
    0.70
     ovat
    0.69
     komple
    0.68
    POSITIVE LOGITS
    uuuu
    0.88
    𝗬
    0.77
    uña
    0.76
    ظر
    0.75
    ྵ
    0.75
    WH
    0.73
    Walls
    0.73
    Ethics
    0.71
    𝗨
    0.71
    Wheel
    0.70
    Activations Density 0.000%

    No Known Activations