© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15875
    Prev
    Next
    INDEX
    Explanations

    past times; galvanized

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

    The neuron selectively activates on numeric tokens—especially multi-digit numbers and decimals.

    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
    上述
    0.88
    ồng
    0.81
    その他
    0.78
    三人
    0.77
    クリック
    0.75
    他
    0.75
    он
    0.73
    大胆
    0.73
    否
    0.72
     Plummer
    0.71
    POSITIVE LOGITS
    ά
    0.71
    ंना
    0.70
     notizie
    0.70
    放題
    0.69
    ষণের
    0.69
     suscit
    0.69
     renowned
    0.67
    zione
    0.66
    studded
    0.66
    pä
    0.66
    Activations Density 0.000%

    No Known Activations