© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124064
    Prev
    Next
    INDEX
    Explanations

    foreach loops

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

    The neuron detects occurrences of the “foreach” iteration keyword in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     avec
    -2.67
    ৢ
    -2.39
    𔘓
    -2.13
     Vereinigten
    -2.11
     групи
    -2.11
    ]
    -2.06
     glede
    -2.03
     {
    -2.03
     variously
    -2.00
     dieser
    -1.98
    POSITIVE LOGITS
    They
    2.83
    獁
    2.56
    ers
    2.44
    There
    2.33
    It
    2.27
     tutup
    2.27
     inginkan
    2.16
    Sistema
    2.14
     車場
    2.13
     sensibilité
    2.13
    Activations Density 0.002%

    No Known Activations