© 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. 10-GEMMASCOPE-RES-131K
    7. 69463
    Prev
    Next
    INDEX
    Explanations

    code and system calls

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

    This neuron detects programming-language code structure, especially function definitions and their block delimiters (e.g. the “func” keyword and opening braces).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -2.20
     their
    -2.06
     this
    -1.84
    ﻷ
    -1.80
     where
    -1.77
     junger
    -1.70
     team
    -1.66
     involved
    -1.59
    
    -1.59
     area
    -1.57
    POSITIVE LOGITS
     mengumumkan
    1.74
     atasan
    1.72
     sebel
    1.70
     作り方
    1.64
     praktis
    1.61
     teknologi
    1.61
    Médaille
    1.61
     chré
    1.59
     delapan
    1.58
    申し上げます
    1.57
    Activations Density 0.374%

    No Known Activations