© 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. 14219
    Prev
    Next
    INDEX
    Explanations

    Eliza, Holden, cstdio

    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
    .
    -3.25
     "
    -2.59
    ');
    -2.42
    );
    -2.36
    .</
    -2.31
    f
    -2.30
    .'
    -2.28
     Until
    -2.28
     incomparable
    -2.27
     巨人
    -2.27
    POSITIVE LOGITS
    钇
    2.84
    縂
    2.83
    韪
    2.80
    ☫
    2.75
    谂
    2.70
    珢
    2.59
     היתה
    2.56
    颳
    2.47
    
    2.47
    ズニー
    2.47
    Activations Density 0.053%

    No Known Activations