© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43463
    Prev
    Next
    INDEX
    Explanations

    Windows file operations

    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
    橚
    -2.38
     digitais
    -1.95
    .《
    -1.90
    ڧ
    -1.85
     commonly
    -1.85
     キャンペーン
    -1.78
     борьбе
    -1.77
    $
    -1.77
     abundant
    -1.73
     eds
    -1.73
    POSITIVE LOGITS
     and
    2.30
     you
    1.90
    步伐
    1.87
    摒
    1.86
     «
    1.84
    //"
    1.77
     andere
    1.76
     reempla
    1.75
    ',
    1.73
     Of
    1.73
    Activations Density 0.060%

    No Known Activations