© 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. 34-GEMMASCOPE-RES-131K
    7. 98913
    Prev
    Next
    INDEX
    Explanations

    documentation generation tools

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

    The neuron is triggered by numeric strings—especially version numbers, dates/times, and other digit-heavy tokens in documentation headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    🧵
    -0.93
     tarp
    -0.77
     Jol
    -0.77
     bloodstream
    -0.76
    магази
    -0.75
     आइटम
    -0.72
    цький
    -0.72
     gasoline
    -0.71
    acide
    -0.71
    ツイート
    -0.69
    POSITIVE LOGITS
     documentation
    2.61
    Documentation
    2.19
    documentation
    2.14
     Documentation
    2.11
    doc
    2.00
     doc
    1.98
     docs
    1.91
    Doc
    1.85
     Doc
    1.85
     documenting
    1.71
    Activations Density 0.280%

    No Known Activations