© 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. 34-GEMMASCOPE-RES-131K
    7. 106311
    Prev
    Next
    INDEX
    Explanations

    compilation and GLSL code

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

    The neuron fires on programming-style tokens and API calls—especially OpenGL shader loading code like the “glShaderSource(…)” call.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     zahrani
    -0.85
    Jegyzőkönyv
    -0.80
    र्जा
    -0.78
    ocin
    -0.77
     ormai
    -0.76
     starker
    -0.74
     WooCommerce
    -0.74
     COURSES
    -0.74
    ),"
    -0.72
    FAULT
    -0.71
    POSITIVE LOGITS
     compilation
    1.16
     compiling
    0.98
     compilations
    0.95
    Compilation
    0.94
     compiles
    0.94
     compile
    0.92
    Compile
    0.91
     GL
    0.88
    compilation
    0.87
     Slo
    0.87
    Activations Density 0.009%

    No Known Activations