© 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. 10-GEMMASCOPE-RES-131K
    7. 11478
    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
    w
    -1.96
    k
    -1.79
     has
    -1.78
     {
    -1.77
     dies
    -1.72
    N
    -1.61
    *
    -1.59
     was
    -1.57
     стал
    -1.57
     появляется
    -1.54
    POSITIVE LOGITS
     retrô
    1.86
     guapos
    1.85
    .
    1.85
     Hinsicht
    1.80
    但是在
    1.78
    趼
    1.74
    但
    1.74
    gambarkan
    1.73
     einzel
    1.70
     stuks
    1.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.