© 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. 22-GEMMASCOPE-RES-131K
    7. 13955
    Prev
    Next
    INDEX
    Explanations

    while true condition

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

    The neuron detects infinite loops, i.e. occurrences of “while (true)” (or equivalent) loop constructs.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ógica
    -1.04
     miasto
    -0.98
     jaka
    -0.96
     تمام
    -0.96
     wła
    -0.94
    xmlhttp
    -0.93
    Portail
    -0.91
    λλά
    -0.91
     என்று
    -0.91
    liptical
    -0.90
    POSITIVE LOGITS
     teneur
    0.95
    ～」
    0.95
     scroll
    0.91
    このように
    0.87
    Scroll
    0.87
    Subject
    0.85
    Assuming
    0.85
    /**
    0.81
    ueves
    0.81
    復興
    0.81
    Activations Density 0.004%

    No Known Activations