© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98987
    Prev
    Next
    INDEX
    Explanations

    function definition return

    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
    ↵
    -2.11
     Its
    -1.65
     my
    -1.62
    了一句
    -1.60
    眉头
    -1.60
    稣
    -1.59
    -
    -1.59
    によく
    -1.57
     It
    -1.53
    acea
    -1.53
    POSITIVE LOGITS
    墬
    1.64
    These
    1.61
    Kedua
    1.59
     土産
    1.54
     على
    1.46
    8
    1.45
    江西
    1.45
     現在
    1.45
     将
    1.43
    重大
    1.42
    Activations Density 0.026%

    No Known Activations