© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123482
    Prev
    Next
    INDEX
    Explanations

    Python tracebacks

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

    the word "Traceback" in programming error messages and stack traces.

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

    This neuron detects code-specific identifiers, such as class or function names and error/exception labels.

    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
    4
    -3.41
     halben
    -3.31
     einzigen
    -3.17
    橚
    -3.11
    6
    -3.06
     gewünschten
    -2.80
    3
    -2.73
    牁
    -2.72
    ”,
    -2.67
     ursprünglichen
    -2.64
    POSITIVE LOGITS
    鶿
    3.27
    錞
    3.25
    ܆
    3.19
    翃
    2.84
    鲼
    2.73
    ︐
    2.72
    饜
    2.67
    ୬
    2.67
    ꯶
    2.61
    
    2.61
    Activations Density 0.001%

    No Known Activations