© 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. 10-GEMMASCOPE-RES-131K
    7. 21245
    Prev
    Next
    INDEX
    Explanations

    special characters followed by code or words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     varier
    -1.77
     薬局
    -1.62
    Режи
    -1.59
    urs
    -1.55
    .*")]
    -1.54
    遢
    -1.52
    냑
    -1.52
    tene
    -1.52
     mereka
    -1.51
    
    -1.47
    POSITIVE LOGITS
     is
    1.70
    
    1.51
     innych
    1.50
    VIATIONS
    1.47
     [
    1.43
    alugar
    1.43
     aislada
    1.41
     last
    1.39
     or
    1.38
     seguras
    1.36
    Activations Density 0.004%

    No Known Activations