© 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. 119102
    Prev
    Next
    INDEX
    Explanations

    boolean settings

    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_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
    However
    -0.98
     memiliki
    -0.96
    Aç
    -0.96
    有不少
    -0.95
     Schönheit
    -0.93
    になりますが
    -0.91
    つづく
    -0.91
     Pläne
    -0.90
    ésar
    -0.90
     квіт
    -0.90
    POSITIVE LOGITS
     bool
    2.13
     boolean
    1.95
     flag
    1.91
    bool
    1.87
    Bool
    1.73
     mode
    1.68
    boolean
    1.66
    Flag
    1.65
    BOOL
    1.63
     enabled
    1.61
    Activations Density 0.054%

    No Known Activations