© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115699
    Prev
    Next
    INDEX
    Explanations

    programming keywords and code constructs

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

    The neuron fires on leading indentation (whitespace) tokens in code, marking the starts of indented code blocks and 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_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
    мам
    -0.94
     üçün
    -0.91
     useAppContext
    -0.88
    ájá
    -0.86
    وتو
    -0.85
     TabLayout
    -0.83
    Their
    -0.83
     if
    -0.82
     RouterModule
    -0.82
    lada
    -0.81
    POSITIVE LOGITS
    var
    1.50
    late
    1.48
    final
    1.46
    bool
    1.38
     final
    1.28
     late
    1.22
    double
    1.16
     List
    1.10
    static
    1.08
     bool
    1.08
    Activations Density 0.001%

    No Known Activations