© 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. 34-GEMMASCOPE-RES-131K
    7. 37757
    Prev
    Next
    INDEX
    Explanations

    software patches

    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
     गणना
    -0.79
    npm
    -0.77
    Basement
    -0.73
    Puerto
    -0.71
     println
    -0.70
    🕐
    -0.69
    Aless
    -0.69
    Дере
    -0.69
     calculator
    -0.69
    Дорогие
    -0.68
    POSITIVE LOGITS
     patch
    3.84
     patches
    3.53
    patch
    3.09
     Patch
    3.00
    patches
    2.95
    Patch
    2.94
    PATCH
    2.63
     Patches
    2.61
    Patches
    2.50
     PATCH
    2.34
    Activations Density 0.154%

    No Known Activations