© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58167
    Prev
    Next
    INDEX
    Explanations

    programming forEach loops

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

    The neuron is triggered by occurrences of the “forEach” method call.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ↵
    -2.45
    𐑂
    -2.45
     vidas
    -2.45
    嘥
    -2.34
     dieser
    -2.28
    section
    -2.28
    y
    -2.27
     hierbas
    -2.25
     producen
    -2.19
     gelangt
    -2.17
    POSITIVE LOGITS
     is
    3.03
    胧
    2.72
    龊
    2.66
    嗚
    2.48
    냠
    2.45
    $.
    2.38
     garg
    2.31
    霂
    2.31
     она
    2.28
    麽
    2.25
    Activations Density 0.001%

    No Known Activations