© 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. 83974
    Prev
    Next
    INDEX
    Explanations

    also followed by verb

    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
    drawSprites
    -1.46
    </i>
    -1.39
     "";
    -1.38
     skóra
    -1.38
    ↵↵↵
    -1.35
    "]);
    -1.34
     "");
    -1.32
    *{-
    -1.31
    .,
    -1.27
    ,“
    -1.27
    POSITIVE LOGITS
     смесь
    1.39
     fallu
    1.38
    PLICATION
    1.37
     novas
    1.36
     posible
    1.36
     juft
    1.34
     reafon
    1.34
    ógicas
    1.30
    Mereka
    1.29
     defire
    1.29
    Activations Density 0.028%

    No Known Activations