© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79292
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by curly brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мани
    0.49
     Mannschaft
    0.48
    霭
    0.48
     conduz
    0.47
     образ
    0.44
    简洁
    0.44
     नहीं
    0.44
     избран
    0.43
     McCullough
    0.43
     ਨਹੀਂ
    0.42
    POSITIVE LOGITS
     會
    0.44
    recursion
    0.43
     recursion
    0.42
    述
    0.42
    cry
    0.40
    的值
    0.39
    #'
    0.39
     形
    0.39
     participle
    0.38
     vaso
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.