© 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. 64409
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    The neuron strongly responds to code‐token “commands” or identifiers—i.e. programming keywords and function/method names (like include, float, reset, close, shift, True, etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     اخیر
    -1.00
     Meksi
    -0.98
    OVERVIEW
    -0.93
    ској
    -0.89
    COURS
    -0.87
    $+\
    -0.87
     makam
    -0.86
    
    -0.86
    uró
    -0.85
    !!</
    -0.85
    POSITIVE LOGITS
     again
    1.15
    再次
    0.89
    again
    0.87
     снова
    0.87
     監督
    0.82
    Again
    0.80
     Again
    0.79
    Mesmo
    0.78
     Insured
    0.76
    insured
    0.75
    Activations Density 0.001%

    No Known Activations