© 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. 67543
    Prev
    Next
    INDEX
    Explanations

    spatial and temporal distance

    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
    诸多
    -1.78
    噲
    -1.73
    最后由
    -1.59
    الحي
    -1.58
    情報は
    -1.56
    那样
    -1.55
    ต่างๆ
    -1.48
    ㌧
    -1.47
     sadece
    -1.46
    嘮
    -1.46
    POSITIVE LOGITS
    )
    1.94
    ",
    1.77
     also
    1.75
    ”
    1.73
    “
    1.63
    x
    1.62
     nostre
    1.59
    ни
    1.57
    ."
    1.52
    \}}
    1.51
    Activations Density 0.002%

    No Known Activations