© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103288
    Prev
    Next
    INDEX
    Explanations

    actions of

    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
     that
    -1.83
     versátil
    -1.67
     and
    -1.64
     because
    -1.63
     každý
    -1.58
     where
    -1.55
    lapsingToolbar
    -1.54
    uminense
    -1.54
     befe
    -1.50
     voordat
    -1.45
    POSITIVE LOGITS
    謌
    1.88
     требует
    1.63
     означает
    1.57
     станет
    1.55
    ”,
    1.55
     Of
    1.55
     стал
    1.52
    可能会
    1.52
     compositeur
    1.50
     visse
    1.50
    Activations Density 0.086%

    No Known Activations