© 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. 73736
    Prev
    Next
    INDEX
    Explanations

    better place because

    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
    同じく
    -1.63
     pourriez
    -1.53
     soothe
    -1.52
    不动
    -1.48
     other
    -1.44
     still
    -1.40
    不下
    -1.38
    もはや
    -1.37
    ACIONAL
    -1.36
    その時
    -1.36
    POSITIVE LOGITS
    ;
    1.61
    first
    1.43
    more
    1.42
    2
    1.41
    这
    1.40
    些
    1.39
     系统
    1.35
    المصدر
    1.34
    study
    1.31
    known
    1.29
    Activations Density 0.011%

    No Known Activations