© 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. 64619
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     tests
    -0.91
    vcut
    -0.87
     knowing
    -0.83
     начала
    -0.82
     строительства
    -0.81
    Guards
    -0.81
     characters
    -0.80
     [
    -0.80
     handmade
    -0.80
     question
    -0.79
    POSITIVE LOGITS
    autorelease
    1.17
    कि
    0.91
    )।
    0.90
    ですよね
    0.88
     वो
    0.88
    こんな
    0.86
    ForType
    0.86
    lež
    0.86
     modalités
    0.85
    २
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.