© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16018
    Prev
    Next
    INDEX
    Explanations

    file path or string literal

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

    This neuron spotlights code tokens referring to file‐ and path‐handling (e.g. “file”, “filename”, “path”, “abspath”, imports like “os”).

    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
     anything
    -1.04
     Wappen
    -1.01
     everything
    -0.97
     after
    -0.97
     when
    -0.96
     see
    -0.96
     anyone
    -0.92
     quick
    -0.92
     becoming
    -0.91
     his
    -0.91
    POSITIVE LOGITS
    //'
    1.07
     tatouage
    1.06
    //"
    1.05
    //.
    1.05
    izadas
    1.00
    ﹪
    1.00
     laug
    0.97
     Donato
    0.96
    edade
    0.94
    uestos
    0.94
    Activations Density 0.022%

    No Known Activations