© 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. 9698
    Prev
    Next
    INDEX
    Explanations

    function arguments or parameters

    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
     siè
    -1.77
     pourront
    -1.76
    launched
    -1.72
    automatically
    -1.70
     inond
    -1.69
     symptômes
    -1.69
    ፨
    -1.69
    鼯
    -1.68
     ſol
    -1.67
     enthou
    -1.64
    POSITIVE LOGITS
     for
    1.85
     taking
    1.79
     data
    1.78
     made
    1.73
     on
    1.73
     by
    1.71
     not
    1.69
     find
    1.66
     uses
    1.65
     new
    1.64
    Activations Density 0.018%

    No Known Activations