© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25311
    Prev
    Next
    INDEX
    Explanations

    file path or urlpath

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

    The neuron fires on code identifiers and configuration keys named “path” (especially the uppercase constant PATH or URL_PATH).

    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
     coelho
    -0.89
     boneca
    -0.87
     Construction
    -0.87
     ۵
    -0.86
     巧克力
    -0.85
    salomon
    -0.83
     ۴
    -0.83
     meleg
    -0.82
     okrę
    -0.82
     rapor
    -0.82
    POSITIVE LOGITS
     смета
    1.11
     within
    1.05
     path
    1.02
    mados
    1.00
     Dien
    0.98
    plona
    0.96
     бампер
    0.96
    rasil
    0.94
    绉
    0.93
     ppb
    0.93
    Activations Density 0.017%

    No Known Activations