© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58345
    Prev
    Next
    INDEX
    Explanations

    gtk graphical libraries

    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
    場は
    -2.59
    顚
    -2.50
    ︐
    -2.47
    汩
    -2.38
    ：
    -2.30
     its
    -2.27
    with
    -2.22
    while
    -2.22
    t
    -2.17
    诶
    -2.17
    POSITIVE LOGITS
    ."
    2.55
    ↵↵
    2.52
    牁
    2.39
    $
    2.33
    на
    2.33
     gebeten
    2.25
    ilta
    2.19
     anstatt
    2.16
     ilustración
    2.09
    derdag
    2.05
    Activations Density 0.003%

    No Known Activations