© 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. 10-GEMMASCOPE-RES-131K
    7. 100420
    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
    “
    -2.64
    ”;
    -2.53
     vår
    -2.52
    腼
    -2.48
    ОВО
    -2.34
    槩
    -2.30
    the
    -2.30
    Ꮚ
    -2.28
    -
    -2.25
    -2.23
    POSITIVE LOGITS
     not
    2.86
     now
    2.80
     to
    2.69
    潮流
    2.52
    最重要
    2.50
     generan
    2.42
     as
    2.39
     still
    2.33
     allegedly
    2.31
     has
    2.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.