© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 74969
    Prev
    Next
    INDEX
    Explanations

    enumerated items or etc

    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
    歟
    -1.53
     grupp
    -1.45
    핌
    -1.39
     illustre
    -1.36
     vuitton
    -1.28
     วิ
    -1.26
     ")");
    -1.26
     sayfas
    -1.25
    "%
    -1.23
    恚
    -1.23
    POSITIVE LOGITS
     then
    1.95
     basically
    1.88
     not
    1.86
     even
    1.86
     mostly
    1.84
     but
    1.82
     maybe
    1.80
     just
    1.79
     mainly
    1.72
     obviously
    1.70
    Activations Density 0.068%

    No Known Activations