© 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. 34-GEMMASCOPE-RES-131K
    7. 1737
    Prev
    Next
    INDEX
    Explanations

    code and comments

    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_34/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
     Halloween
    -0.73
    キャン
    -0.70
    꺽
    -0.70
    Norm
    -0.69
    ByPrimaryKey
    -0.69
     Keynes
    -0.69
    plyr
    -0.68
     totalCount
    -0.68
    boutin
    -0.68
    हाय
    -0.67
    POSITIVE LOGITS
     Tse
    0.69
    Requisitos
    0.69
    セキュリティ
    0.64
     bangles
    0.63
     Uphol
    0.63
    解锁
    0.61
    coordinates
    0.61
    step
    0.60
     सुर
    0.59
     Postage
    0.59
    Activations Density 0.064%

    No Known Activations