© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12714
    Prev
    Next
    INDEX
    Explanations

    parsing instructions into structured data

    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_7_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
     袖
    1.70
     디자인
    1.62
    ள்க
    1.60
     Thiết
    1.60
    鉋
    1.58
     그래
    1.58
     높
    1.58
     강의
    1.55
     plug
    1.55
     Knit
    1.54
    POSITIVE LOGITS
    residual
    1.10
    राजनी
    0.95
     spontaneous
    0.94
     السياسي
    0.93
    Nathan
    0.93
    astere
    0.92
    untamento
    0.91
    uran
    0.90
    eur
    0.90
    [](
    0.90
    Activations Density 0.090%

    No Known Activations