© 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. 99237
    Prev
    Next
    INDEX
    Explanations

    timestamps, urls, and other text

    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
     '
    -1.98
     the
    -1.98
    ...
    -1.96
    /
    -1.91
    out
    -1.70
    -
    -1.66
    ...?
    -1.64
     few
    -1.58
     ...
    -1.52
    --
    -1.46
    POSITIVE LOGITS
    」、「
    1.94
    QUÉ
    1.60
     環
    1.57
    umenta
    1.56
    umentar
    1.55
    后感
    1.53
     ‘‘
    1.51
     then
    1.50
    》,
    1.48
    といえば
    1.48
    Activations Density 0.011%

    No Known Activations