© 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. 108371
    Prev
    Next
    INDEX
    Explanations

    programming while loops

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

    The neuron specializes in spotting programming‐language tokens—especially numeric literals and code punctuation (braces, semicolons, parentheses) in code snippets.

    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
    otheby
    -1.00
    咗
    -0.95
     sklep
    -0.93
    reszcie
    -0.91
    𝙹
    -0.90
     hasattr
    -0.88
    なりません
    -0.86
    あとは
    -0.86
    הו
    -0.86
     Алла
    -0.85
    POSITIVE LOGITS
     while
    9.38
    while
    7.47
     mientras
    6.25
     mentre
    6.03
     whilst
    5.50
     enquanto
    5.50
    While
    5.44
     WHILE
    5.25
     While
    4.91
    WHILE
    4.72
    Activations Density 0.037%

    No Known Activations