© 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. 34-GEMMASCOPE-RES-131K
    7. 73295
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     or
    -0.95
     minuter
    -0.92
     for
    -0.91
    {#
    -0.89
     januari
    -0.86
     NOVEMBER
    -0.85
     other
    -0.83
    出来ない
    -0.81
     OCTOBER
    -0.81
     give
    -0.80
    POSITIVE LOGITS
     Zelensky
    1.02
    
    0.97
     Miracles
    0.95
     opravdu
    0.94
    reibe
    0.93
     okazji
    0.92
     angene
    0.91
     caixas
    0.91
     AMAZING
    0.90
     brukar
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.