© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91966
    Prev
    Next
    INDEX
    Explanations

    programming loops

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

    This neuron detects the loop-index expressions in for-loop headers (the numeric iteration bounds and related tokens in "for (int i = 0; i < …; i++)").

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     samego
    -0.85
    ()=>{
    -0.83
    includes
    -0.81
    nope
    -0.81
    chefs
    -0.81
    粄
    -0.80
    ennia
    -0.80
    他们
    -0.79
     آنها
    -0.79
     stessa
    -0.78
    POSITIVE LOGITS
    ;
    0.96
     ещё
    0.77
    !
    0.77
    matico
    0.77
    disposing
    0.77
     там
    0.75
    kken
    0.75
    edades
    0.74
    AJAS
    0.73
     Objects
    0.72
    Activations Density 0.003%

    No Known Activations