© 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. 22-GEMMASCOPE-RES-131K
    7. 16659
    Prev
    Next
    INDEX
    Explanations

    function calls

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ⁛
    -1.50
    และ
    -1.48
    ྅
    -1.42
    serviceWorker
    -1.41
    𐄁
    -1.41
    thmus
    -1.37
    淖
    -1.35
     ",";
    -1.34
     فقط
    -1.31
     mirando
    -1.31
    POSITIVE LOGITS
    },
    1.52
    ,
    1.49
     achieving
    1.46
    钲
    1.44
     maintaining
    1.37
    月から
    1.34
     видел
    1.34
     påvir
    1.32
    ﹆
    1.31
     determining
    1.30
    Activations Density 0.002%

    No Known Activations