© 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. 99400
    Prev
    Next
    INDEX
    Explanations

    menu offerings and choices

    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
     in
    -1.11
     cookies
    -1.02
     coffee
    -1.00
    gten
    -0.96
     chocolate
    -0.96
     candy
    -0.94
     Unterrichts
    -0.93
    corns
    -0.92
     vinaigre
    -0.91
     Desember
    -0.90
    POSITIVE LOGITS
     menu
    1.73
     specials
    1.66
     choices
    1.50
     items
    1.47
     listed
    1.42
     choice
    1.30
     item
    1.30
     offerings
    1.25
     options
    1.23
     Specials
    1.19
    Activations Density 0.018%

    No Known Activations