© 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. 10-GEMMASCOPE-RES-131K
    7. 68409
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     and
    -2.00
    readFileSync
    -1.88
    TestBed
    -1.78
     will
    -1.69
    🤤
    -1.62
     are
    -1.61
    zers
    -1.61
    榈
    -1.59
    strator
    -1.59
    ANSA
    -1.58
    POSITIVE LOGITS
     gefe
    1.50
    튿
    1.50
     некоторых
    1.39
     хорошего
    1.38
     hés
    1.37
     ajouter
    1.37
    龉
    1.37
     estrategia
    1.33
     cliquer
    1.33
    落ちて
    1.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.