© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128981
    Prev
    Next
    INDEX
    Explanations

    clinical predictors

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

    lines or symbols that separate document sections, such as dashed lines, equal signs, or decorative elements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。"
    -2.91
     Hinsicht
    -2.55
     will
    -2.50
    ၟ
    -2.42
    」（
    -2.27
     examined
    -2.27
    ！"
    -2.27
     Only
    -2.22
    🌸
    -2.20
    Only
    -2.19
    POSITIVE LOGITS
    ⬈
    2.47
    a
    2.45
     blockbuster
    2.36
     coût
    2.34
     quintessential
    2.33
    殽
    2.27
     régal
    2.22
     derniers
    2.22
    快要
    2.19
     terrific
    2.17
    Activations Density 0.003%

    No Known Activations