© 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. 87074
    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
    economic
    -1.04
    Highland
    -0.90
     Dong
    -0.90
    譴
    -0.87
     and
    -0.87
    François
    -0.85
    Carolyn
    -0.85
     правительства
    -0.84
    ndig
    -0.84
    rás
    -0.84
    POSITIVE LOGITS
     приготовить
    1.05
     evokes
    0.94
     disebabkan
    0.93
     determinar
    0.90
     évaluations
    0.90
    遭遇
    0.88
    图源
    0.88
     ascertaining
    0.88
    到了
    0.87
     forming
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.