© 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. 106352
    Prev
    Next
    INDEX
    Explanations

    php code strings

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

    This neuron detects filesystem or URL path segments—i.e. slash-separated directory or file names in code and links.

    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
     accumulates
    -0.75
     aastal
    -0.74
     refiere
    -0.74
     inflicted
    -0.73
     prescriptions
    -0.69
    dison
    -0.69
    ńskiej
    -0.68
    膣
    -0.68
     intimately
    -0.68
    haust
    -0.67
    POSITIVE LOGITS
    $_['
    0.90
     моди
    0.85
    Alaska
    0.85
     Saleh
    0.79
     oc
    0.78
    SortOrder
    0.78
     ULT
    0.77
     pav
    0.76
     Alaska
    0.75
    cler
    0.74
    Activations Density 0.022%

    No Known Activations