© 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. 22-GEMMASCOPE-RES-131K
    7. 33794
    Prev
    Next
    INDEX
    Explanations

    lists of items, code snippets

    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_22/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
    LINEAR
    -1.01
    oncesto
    -0.94
     manualidades
    -0.93
    Another
    -0.87
     endforeach
    -0.87
     Another
    -0.86
    ʿ
    -0.85
    のだが
    -0.85
     suplementos
    -0.84
    ूरत
    -0.84
    POSITIVE LOGITS
     electrica
    0.88
     Othello
    0.87
     new
    0.85
     alcune
    0.84
    findOne
    0.84
    恚
    0.84
     some
    0.83
    ركات
    0.82
     Joke
    0.82
    还会
    0.81
    Activations Density 0.056%

    No Known Activations