© 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. 22-GEMMASCOPE-RES-131K
    7. 72758
    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
     five
    -1.12
     Initially
    -1.07
     perumahan
    -1.06
     eight
    -1.05
     erneut
    -1.02
     starts
    -1.01
     enthusiastic
    -1.00
     six
    -1.00
     eleven
    -1.00
     with
    -0.99
    POSITIVE LOGITS
    fatalError
    1.17
    袛
    1.12
     唯美
    1.09
    푆
    1.07
    鮠
    1.07
    Ј
    1.05
    
    1.03
     電動
    1.02
     Questo
    1.01
     pengar
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.