© 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. 127733
    Prev
    Next
    INDEX
    Explanations

    The neuron is activated by C/C++ preprocessor include directives (lines beginning with “#include”).

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

    code comments and copyright notices

    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
     möglicherweise
    -1.02
     viena
    -0.95
     veiks
    -0.90
     būt
    -0.89
     теперь
    -0.85
    mortar
    -0.85
    več
    -0.85
    ircut
    -0.84
     Antik
    -0.83
     our
    -0.82
    POSITIVE LOGITS
    platten
    1.09
     jego
    1.02
     encargada
    0.99
     traseiro
    0.98
    鲥
    0.96
     legislación
    0.94
     туры
    0.93
    проект
    0.92
    фотография
    0.92
     básica
    0.92
    Activations Density 0.004%

    No Known Activations