© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16521
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    The main thing this neuron does is detect numeric literals (numbers) in code.

    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
    <0xEB>
    -1.10
     şeker
    -1.09
     教程
    -1.08
    МУ
    -1.03
     interpolate
    -1.02
    ₚ
    -1.02
     aastal
    -1.01
    hoka
    -1.00
    NEN
    -1.00
    ویر
    -1.00
    POSITIVE LOGITS
     which
    0.95
    ↵↵
    0.94
     and
    0.93
     often
    0.91
     use
    0.91
    ");
    0.90
     start
    0.89
    )=>{
    
    0.88
     all
    0.87
     as
    0.85
    Activations Density 0.010%

    No Known Activations