© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117928
    Prev
    Next
    INDEX
    Explanations

    forwards coach

    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
     premiers
    -0.90
     premi
    -0.80
    蘋
    -0.73
    Premi
    -0.73
    unier
    -0.71
     Lettre
    -0.69
    韵
    -0.67
    ódnica
    -0.66
     هاي
    -0.66
     πρω
    -0.66
    POSITIVE LOGITS
    ходили
    0.81
    MB
    0.81
     square
    0.76
     Square
    0.75
    square
    0.70
    getFont
    0.70
    кологи
    0.69
     MB
    0.69
     wr
    0.68
    kozások
    0.68
    Activations Density 0.015%

    No Known Activations