© 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. 25943
    Prev
    Next
    INDEX
    Explanations

    javascript variable and function declarations

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

    This neuron activates on programming language keywords and syntax tokens (e.g., var, function, import, class).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     intricacies
    -0.92
     !!!
    -0.90
     distinctly
    -0.90
     Additional
    -0.89
     ONLY
    -0.89
     noticeably
    -0.88
     pushed
    -0.86
     placed
    -0.85
     oftentimes
    -0.84
     neatly
    -0.82
    POSITIVE LOGITS
     więks
    1.01
     شخصية
    1.01
    veness
    0.91
     フィギュア
    0.90
    getSystemService
    0.88
    TargetException
    0.88
     vaak
    0.86
    taan
    0.86
    vaders
    0.86
     Metropolitan
    0.85
    Activations Density 0.033%

    No Known Activations