© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43058
    Prev
    Next
    INDEX
    Explanations

    system include or calls

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

    This neuron detects occurrences of the C header “unistd” in #include directives.

    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
     menyen
    -2.75
    ”？
    -2.72
     放題
    -2.67
     GOtt
    -2.67
     插图
    -2.66
     plak
    -2.66
    焿
    -2.66
    注意事
    -2.63
     vixion
    -2.61
     火鍋
    -2.58
    POSITIVE LOGITS
     reconoci
    2.61
     But
    2.53
    D
    2.38
    ↵↵
    2.36
     peque
    2.34
     olvid
    2.34
     orgull
    2.27
    ે
    2.27
    E
    2.27
     enclosed
    2.25
    Activations Density 0.019%

    No Known Activations