© 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. 38639
    Prev
    Next
    INDEX
    Explanations

    CRLF, MIME, HTTP, serial, legal, drugstore, MEMS

    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
    Only
    -2.38
    Usually
    -2.23
    Generally
    -2.22
    Surprisingly
    -2.20
    Shortly
    -2.17
    Obviously
    -2.16
    Those
    -2.13
    During
    -2.13
    There
    -2.13
    Very
    -2.08
    POSITIVE LOGITS
    蹑
    2.17
    悻
    1.73
    猛地
    1.73
     conhecido
    1.70
    @[+][
    1.68
     spanning
    1.64
     controver
    1.61
     revered
    1.61
     replete
    1.60
    ARIUS
    1.58
    Activations Density 0.000%

    No Known Activations