© 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. 34-GEMMASCOPE-RES-131K
    7. 62428
    Prev
    Next
    INDEX
    Explanations

    php foreach

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

    This neuron fires on indented lines of source code (the leading whitespace that marks code blocks).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ľov
    -0.87
     cocaína
    -0.83
     Around
    -0.81
    硯
    -0.79
     cortado
    -0.79
    ousel
    -0.78
    هنگ
    -0.77
     autour
    -0.77
    cão
    -0.76
     betale
    -0.76
    POSITIVE LOGITS
     against
    6.47
    foreach
    5.72
     foreach
    4.44
    Against
    3.77
    against
    3.70
     Against
    3.50
    對
    3.27
     против
    3.20
     gegen
    3.19
    对
    3.17
    Activations Density 0.026%

    No Known Activations