© 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. 127689
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on file‐path tokens in include/import directives, i.e. when a header or module filename appears in an `#include` or similar statement.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    code includes and definitions

    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
    Negative Logits
     detalló
    -1.20
     Ива
    -1.06
    Sú
    -1.05
     sœurs
    -1.05
     mencionó
    -1.02
    ⅙
    -1.01
    according
    -1.01
    міст
    -1.00
    México
    -0.98
     капю
    -0.97
    POSITIVE LOGITS
     ytterligare
    1.16
     Theologie
    1.11
     сочи
    1.09
     control
    1.09
     настройки
    1.08
     Toko
    1.08
     нарушения
    1.05
     REFUND
    1.04
     掃除
    1.04
     GRATIS
    1.03
    Activations Density 0.008%

    No Known Activations