© 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. 127303
    Prev
    Next
    INDEX
    Explanations

    shader code

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

    The neuron is activated by the literal token “shader” (in any casing) in code or 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_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
    瑨
    -2.78
     essayé
    -2.59
     sorta
    -2.56
     commencé
    -2.47
    ("");
    -2.39
    ۺ
    -2.39
     protestas
    -2.39
    缡
    -2.39
    
    -2.39
    énus
    -2.38
    POSITIVE LOGITS
    .
    3.36
    蛲
    2.80
    ↵↵
    2.53
    <
    2.52
    to
    2.47
     zwanzig
    2.38
    耵
    2.33
    >
    2.30
    &
    2.28
    two
    2.27
    Activations Density 0.001%

    No Known Activations