© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11835
    Prev
    Next
    INDEX
    Explanations

    code comments

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

    comment lines in source code, particularly those starting with `#` or `*`.

    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
    </em>
    -2.50
    </td>
    -2.22
    quelize
    -2.16
    </h2>
    -2.08
    c
    -2.02
    </sup>
    -1.97
    "];
    -1.91
    chenta
    -1.90
    ximation
    -1.88
    p
    -1.86
    POSITIVE LOGITS
    '
    2.48
     and
    2.27
     Each
    1.93
     "
    1.91
     Either
    1.87
     teile
    1.72
    蹋
    1.70
     Everyone
    1.66
     "-
    1.63
     a
    1.61
    Activations Density 0.143%

    No Known Activations