© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112280
    Prev
    Next
    INDEX
    Explanations

    logging and debugging keywords

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

    references to logging frameworks or debugging utilities in source code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on code tokens related to logging—i.e. identifiers and includes containing “log” or logger-API names.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -2.59
     from
    -1.92
     It
    -1.84
     Usually
    -1.82
     If
    -1.82
     and
    -1.75
     On
    -1.75
     For
    -1.73
     How
    -1.73
     Also
    -1.73
    POSITIVE LOGITS
     GRATU
    1.94
     kado
    1.92
    菒
    1.87
     biber
    1.84
     kazak
    1.81
     intrig
    1.79
     tabak
    1.77
     bunda
    1.77
     anadolu
    1.77
     bambu
    1.76
    Activations Density 0.008%

    No Known Activations