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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86881
    Prev
    Next
    INDEX
    Explanations

    while loops

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

    The neuron is strongly activated by mentions of infinite looping constructs (e.g. “infinite loop,” “while(true)”) in code examples.

    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
    XCTAssertEqual
    -0.83
    ೨
    -0.81
    我最
    -0.79
     kated
    -0.78
    ća
    -0.75
    哂
    -0.74
    Jeudi
    -0.73
     だっ
    -0.72
    addContainer
    -0.71
    厚的
    -0.71
    POSITIVE LOGITS
     while
    3.09
    while
    2.45
     forever
    2.16
     loop
    2.03
     infinite
    1.91
    While
    1.86
     WHILE
    1.83
    forever
    1.78
     mientras
    1.77
     whilst
    1.76
    Activations Density 0.040%

    No Known Activations