© 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. 10-GEMMASCOPE-RES-131K
    7. 11979
    Prev
    Next
    INDEX
    Explanations

    HTML, web, comments, metadata

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML comments in code documentation and web development files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     doivent
    -1.89
    傒
    -1.84
     ludicrous
    -1.84
    튿
    -1.82
     bizarre
    -1.79
    킁
    -1.79
     corrom
    -1.75
     bluz
    -1.71
     semelh
    -1.68
     любой
    -1.67
    POSITIVE LOGITS
     with
    3.16
     from
    2.52
     in
    2.48
     on
    2.31
     as
    2.27
     at
    2.23
     for
    2.09
     just
    1.96
     all
    1.95
     without
    1.88
    Activations Density 0.018%

    No Known Activations