© 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. 34-GEMMASCOPE-RES-131K
    7. 93836
    Prev
    Next
    INDEX
    Explanations

    include directives and C++ code

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

    This neuron detects C/C++ preprocessor include directives (lines with “#include <…>” or “#include "…"`).

    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
    ostream
    -0.90
    CMAKE
    -0.87
    Adr
    -0.77
     kwal
    -0.76
     endl
    -0.75
     express
    -0.75
    structura
    -0.72
    曹
    -0.72
    ümü
    -0.71
    palindrome
    -0.71
    POSITIVE LOGITS
    sf
    1.00
     sf
    0.94
     BMP
    0.82
    違って
    0.76
    irr
    0.75
    YAML
    0.75
     im
    0.75
     glm
    0.71
     लग
    0.71
    ченным
    0.70
    Activations Density 0.017%

    No Known Activations