© 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. 71928
    Prev
    Next
    INDEX
    Explanations

    relative path to library or stylesheet

    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
     عندما
    -2.39
    𒊹
    -2.36
    咵
    -2.30
    ゎ
    -2.28
    よく
    -2.25
    ༛
    -2.23
     angegebenen
    -2.22
    勍
    -2.16
    ～～～～
    -2.16
    》。
    -2.13
    POSITIVE LOGITS
    o
    3.63
    a
    3.38
    e
    3.28
    f
    3.03
    h
    2.98
    as
    2.92
    d
    2.84
    i
    2.73
    y
    2.56
    c
    2.53
    Activations Density 0.007%

    No Known Activations