© 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. 84067
    Prev
    Next
    INDEX
    Explanations

    code punctuation like braces and semicolons

    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
     Tarantino
    -0.92
    CSM
    -0.92
     comesti
    -0.90
     Silverado
    -0.90
     Creta
    -0.88
     fundación
    -0.88
     tiresome
    -0.88
     Øst
    -0.86
     Marquis
    -0.86
    CRAFT
    -0.86
    POSITIVE LOGITS
    heater
    0.79
    ined
    0.79
     
    0.77
    icated
    0.75
     extent
    0.73
    cipated
    0.73
     зад
    0.73
     shock
    0.72
    ority
    0.72
     жи
    0.70
    Activations Density 0.052%

    No Known Activations