© 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. 14884
    Prev
    Next
    INDEX
    Explanations

    log statements

    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
     A
    -1.95
    ;
    -1.68
     My
    -1.67
     Its
    -1.66
     Of
    -1.59
     Ive
    -1.59
    Schriften
    -1.57
    默默
    -1.56
     конечно
    -1.56
     L
    -1.56
    POSITIVE LOGITS
    鐽
    1.74
    缭
    1.63
    joyed
    1.60
     EUG
    1.59
     EGYPT
    1.56
    疍
    1.55
     GIO
    1.54
    ︕
    1.51
     ROMA
    1.51
     GREEK
    1.51
    Activations Density 0.008%

    No Known Activations