© 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. 7938
    Prev
    Next
    INDEX
    Explanations

    investments scam entry beginner

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

    The neuron flags tokens that start off a numbered or bullet‐point list item.

    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
     and
    0.84
    ી
    0.84
    ią
    0.82
     towards
    0.81
     raster
    0.80
    ות
    0.78
    ი
    0.78
    ಲೋ
    0.76
    ীতে
    0.75
     gazing
    0.74
    POSITIVE LOGITS
     этим
    0.82
    ต
    0.79
     Beleza
    0.76
    すべて
    0.76
     причины
    0.74
    是否存在
    0.71
     первую
    0.71
     desapare
    0.68
     オーバー
    0.68
    BODY
    0.67
    Activations Density 0.000%

    No Known Activations