© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68574
    Prev
    Next
    INDEX
    Explanations

    interface and class names

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on C# interface and similar type names that start with a capital “I” (e.g., ITest, ILogger, ISystem) in source code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    A
    -2.73
    D
    -2.16
    E
    -2.13
     rufen
    -2.11
    In
    -2.11
    At
    -1.99
     рассказывает
    -1.98
    O
    -1.94
     longtime
    -1.94
    }{
    -1.93
    POSITIVE LOGITS
    
    2.19
     ,‬
    1.90
    辚
    1.86
    mente
    1.80
    lijk
    1.78
    桄
    1.73
     ſch
    1.72
    咵
    1.70
    isting
    1.67
    鹂
    1.67
    Activations Density 0.008%

    No Known Activations