© 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. 112563
    Prev
    Next
    INDEX
    Explanations

    PrimaryKey, Key, Strengths

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

    words ending in "mp" or containing "crimp" patterns, particularly in technical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    恫
    -2.36
    \
    -2.33
     geniş
    -2.31
     wayward
    -2.23
    段时间
    -2.20
     activado
    -2.19
    絝
    -2.19
     あります
    -2.19
    錚
    -2.17
     pensado
    -2.11
    POSITIVE LOGITS
    us
    3.44
    甞
    2.81
    which
    2.67
    g
    2.63
    to
    2.48
    quelize
    2.48
    ens
    2.41
    ER
    2.39
    k
    2.36
    z
    2.36
    Activations Density 0.002%

    No Known Activations