© 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. 34-GEMMASCOPE-RES-131K
    7. 62789
    Prev
    Next
    INDEX
    Explanations

    code documentation and comments

    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
     drink
    -0.78
     față
    -0.74
    vies
    -0.73
    发布时间
    -0.67
    ẍ
    -0.66
    szön
    -0.65
     pēc
    -0.65
     Sahara
    -0.65
    println
    -0.64
    وشی
    -0.64
    POSITIVE LOGITS
     comments
    2.47
     doc
    2.25
     comment
    2.11
     documentation
    2.05
    avadoc
    2.00
    doc
    1.97
     Doc
    1.84
    注释
    1.83
    Doc
    1.81
     коммента
    1.80
    Activations Density 0.119%

    No Known Activations