© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 123
    Prev
    Next
    INDEX
    Explanations

    python direct execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    <unused326>
    0.97
    名字
    0.97
    rlen
    0.97
    <unused1834>
    0.95
     recognizable
    0.93
    <unused1233>
    0.92
     carelessness
    0.92
    <unused302>
    0.92
     anxieties
    0.92
    classify
    0.92
    POSITIVE LOGITS
     approfond
    0.77
     của
    0.76
     hàng
    0.74
    /
    0.74
     fais
    0.74
     temprano
    0.74
    สำหรับ
    0.73
     contre
    0.73
     prochains
    0.72
     udrž
    0.71
    Activations Density 0.037%

    No Known Activations