© 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. 67141
    Prev
    Next
    INDEX
    Explanations

    agency

    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_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
    </strong>
    -1.73
     then
    -1.52
    <bos>
    -1.46
     bahkan
    -1.43
    </em>
    -1.40
    </h2>
    -1.39
     it
    -1.36
     will
    -1.36
     can
    -1.34
    人了
    -1.26
    POSITIVE LOGITS
    рна
    1.45
    𓋼
    1.29
    ╿
    1.29
     isempty
    1.27
     المعرف
    1.27
    ＝
    1.24
    .',
    1.23
     folie
    1.20
    新たな
    1.18
    ziplin
    1.18
    Activations Density 0.214%

    No Known Activations