© 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. 70808
    Prev
    Next
    INDEX
    Explanations

    Noel and JV

    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
    趼
    -3.70
     Anſ
    -3.34
    蛱
    -3.23
    ⢌
    -3.03
    geſ
    -2.98
    炱
    -2.97
    目前的
    -2.80
     แต่
    -2.80
    ୪
    -2.69
    氿
    -2.61
    POSITIVE LOGITS
    (
    2.89
    >
    2.75
     he
    2.70
    O
    2.48
    The
    2.42
    x
    2.41
    8
    2.38
     clunky
    2.36
    ro
    2.36
    之地
    2.33
    Activations Density 0.018%

    No Known Activations