© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57510
    Prev
    Next
    INDEX
    Explanations

    file extensions and file

    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
     PDF
    -0.93
     pdf
    -0.89
     Michelle
    -0.82
     pink
    -0.81
    Json
    -0.81
    Substituting
    -0.76
     toprak
    -0.75
     diretta
    -0.75
     üzer
    -0.75
     HTML
    -0.75
    POSITIVE LOGITS
     file
    3.20
     files
    3.13
    文件
    2.23
    ファイル
    2.06
    file
    1.98
    文件中
    1.86
    文件的
    1.84
    files
    1.80
     файл
    1.77
     Files
    1.63
    Activations Density 0.199%

    No Known Activations