© 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. 118220
    Prev
    Next
    INDEX
    Explanations

    ui components and web development

    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
     even
    -1.66
     which
    -1.61
     Even
    -1.53
     being
    -1.48
     that
    -1.41
     should
    -1.34
     as
    -1.31
     long
    -1.31
     or
    -1.30
     what
    -1.30
    POSITIVE LOGITS
     malgré
    1.21
     primar
    1.18
    primarily
    1.16
     cinq
    1.13
    despite
    1.12
     BEAUTIFUL
    1.12
    didn
    1.11
     molti
    1.11
    exactly
    1.11
    Legendary
    1.10
    Activations Density 0.001%

    No Known Activations