© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1835
    Prev
    Next
    INDEX
    Explanations

    license, author, package

    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_34/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
     goû
    -1.32
    Tento
    -1.23
     siè
    -1.21
     douze
    -1.20
     pérd
    -1.18
    associated
    -1.18
     quinze
    -1.16
    ⌵
    -1.16
    ཿ
    -1.16
     vín
    -1.16
    POSITIVE LOGITS
     in
    1.45
     to
    1.29
     by
    1.27
     as
    1.23
     over
    1.20
     with
    1.19
     at
    1.15
    ;
    1.11
     for
    1.09
     about
    1.07
    Activations Density 0.001%

    No Known Activations