© 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. 22-GEMMASCOPE-RES-131K
    7. 127968
    Prev
    Next
    INDEX
    Explanations

    This neuron detects C/C++ `#include` directives by firing on the `<` token (and the accompanying `include`) in lines like `#include <header.h>`.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    c++ standard library headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     花纹
    -1.63
     plafon
    -1.61
    ፨
    -1.55
     emballage
    -1.55
     drapeau
    -1.55
     唯美
    -1.55
    𐀀
    -1.54
     排骨
    -1.52
     geene
    -1.52
     romantis
    -1.52
    POSITIVE LOGITS
    ↵↵
    1.68
     U
    1.66
     there
    1.65
     it
    1.64
     D
    1.63
     S
    1.63
     To
    1.52
    M
    1.52
     This
    1.52
    P
    1.52
    Activations Density 0.012%

    No Known Activations