© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58697
    Prev
    Next
    INDEX
    Explanations

    dark twisted reputation

    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
    asında
    -1.83
    Цита
    -1.73
    定価
    -1.68
    私には
    -1.66
    なんとなく
    -1.64
    価格は
    -1.63
    スリ
    -1.63
    历史上
    -1.63
    已经在
    -1.61
    什么的
    -1.60
    POSITIVE LOGITS
     and
    2.38
     also
    1.88
     actually
    1.62
     not
    1.56
     и
    1.48
    袂
    1.47
    และ
    1.47
     even
    1.45
    🏟
    1.44
     kapturem
    1.42
    Activations Density 0.015%

    No Known Activations