© 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. 102843
    Prev
    Next
    INDEX
    Explanations

    denim, Jean, halide, modesty, Link, Differ

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     gazed
    -2.48
    ”.
    -2.42
     Of
    -2.38
     Also
    -2.38
    Of
    -2.28
    ↵↵
    -2.28
     Undoubtedly
    -2.23
     Obviously
    -2.20
     Furthermore
    -2.17
     Somehow
    -2.17
    POSITIVE LOGITS
    臜
    2.84
    鸶
    2.83
    蟊
    2.75
    此事
    2.59
    沵
    2.50
    蛲
    2.39
    菒
    2.38
    𖧵
    2.34
    𓍊
    2.34
    牂
    2.33
    Activations Density 0.001%

    No Known Activations