© 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. 39815
    Prev
    Next
    INDEX
    Explanations

    on and off the field

    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
     not
    -1.89
     How
    -1.64
     Why
    -1.56
     if
    -1.52
     in
    -1.51
     you
    -1.49
     If
    -1.37
     find
    -1.36
     there
    -1.34
     who
    -1.34
    POSITIVE LOGITS
     Dinas
    1.45
    悲しい
    1.44
    -;
    1.42
     čern
    1.41
    #}
    1.39
    peut
    1.38
     niedersachsen
    1.38
     aston
    1.36
     intrigu
    1.35
     zboží
    1.33
    Activations Density 0.019%

    No Known Activations