© 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. 22-GEMMASCOPE-RES-131K
    7. 66613
    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
     if
    -2.08
     by
    -1.95
    などを
    -1.91
     because
    -1.89
    ～～
    -1.86
     unwavering
    -1.86
     unrelenting
    -1.84
    ～！
    -1.83
    ～～～
    -1.83
     gives
    -1.78
    POSITIVE LOGITS
     cũng
    1.98
    ’
    1.86
    きれい
    1.84
    
    1.84
     Dinas
    1.84
    IN
    1.81
    H
    1.81
     disposto
    1.76
    場合には
    1.75
    Y
    1.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.