© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117468
    Prev
    Next
    INDEX
    Explanations

    static Program

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

    This neuron strongly activates on leading whitespace/indentation tokens in code, effectively detecting the indent levels (code block structure) in programming text.

    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
     reúne
    -0.86
    ダード
    -0.85
    criptors
    -0.82
     habiendo
    -0.82
    اديم
    -0.79
    だし
    -0.77
    擧
    -0.77
     kategorii
    -0.76
    guitarra
    -0.75
    salomon
    -0.74
    POSITIVE LOGITS
    static
    2.02
     static
    1.80
     Program
    1.11
     delegate
    0.96
    Program
    0.95
     стихи
    0.88
     PROGRAM
    0.88
     program
    0.87
    JvmStatic
    0.86
    PROGRAM
    0.85
    Activations Density 0.017%

    No Known Activations