© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112845
    Prev
    Next
    INDEX
    Explanations

    code, comments, imports

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

    whitespace indentation, particularly tabs and spaces used for code formatting and structure.

    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
     However
    -2.41
    There
    -1.94
    This
    -1.91
     Saltar
    -1.86
     There
    -1.84
    /**
    -1.79
     acreditar
    -1.78
     These
    -1.73
     concluir
    -1.73
     anunciar
    -1.72
    POSITIVE LOGITS
    ↵
    2.03
     &
    2.03
    垆
    1.91
     dezelve
    1.82
    \
    1.80
    了一句
    1.73
     you
    1.73
     sein
    1.62
     zijn
    1.62
     seine
    1.60
    Activations Density 0.020%

    No Known Activations