© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5053
    Prev
    Next
    INDEX
    Explanations

    i =

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

    This neuron detects occurrences of the loop‐counter variable “i” (and similar integer index variables) in code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Increasing
    0.64
     i
    0.61
    ,__
    0.59
    explored
    0.59
    hythmic
    0.59
     கால
    0.58
     in
    0.56
     Vando
    0.56
     Deferred
    0.55
    otted
    0.55
    POSITIVE LOGITS
    =
    0.83
    $=
    0.66
     $=
    0.63
    =.
    0.60
    ですよね
    0.57
    =-
    0.57
    겐
    0.56
    
    0.52
     =
    0.52
    Ƅ
    0.52
    Activations Density 0.001%

    No Known Activations