© 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. 83370
    Prev
    Next
    INDEX
    Explanations

    date following updated

    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
    WriteLiteral
    -0.83
     commencé
    -0.83
     geliş
    -0.81
     rar
    -0.81
    begins
    -0.80
    〼
    -0.80
    developed
    -0.79
     desenvolvimento
    -0.78
    weren
    -0.77
    ÉR
    -0.77
    POSITIVE LOGITS
     by
    1.07
    нутри
    0.76
     various
    0.70
     же
    0.70
     foresee
    0.70
     as
    0.69
     at
    0.69
    ;
    0.66
     menganggap
    0.66
     eliminates
    0.66
    Activations Density 0.028%

    No Known Activations