Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2852
    Prev
    Next
    INDEX
    Explanations

    namespaces and declarations

    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_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
    JPG
    0.77
    holz
    0.76
     щи
    0.73
    cesso
    0.70
    bonus
    0.69
     elim
    0.68
     surcharge
    0.68
    +
    0.68
    /
    0.67
    [
    0.67
    POSITIVE LOGITS
     ネックレス
    1.42
     ブレスレット
    1.39
     אטאטורק
    1.38
     -->'
    1.33
     FastAPI
    1.30
     スニーカー
    1.30
     مدينة
    1.29
    医药
    1.28
     swagger
    1.28
     春
    1.27
    Activations Density 0.179%

    No Known Activations