© 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. 74509
    Prev
    Next
    INDEX
    Explanations

    try catch throw

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

    The main thing this neuron does is find exception‐handling keywords in code (e.g. try, catch, throw).

    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
    N
    -1.58
    2
    -1.57
    of
    -1.56
    by
    -1.54
    al
    -1.51
    o
    -1.43
     medes
    -1.36
    saying
    -1.35
    c
    -1.34
     graden
    -1.33
    POSITIVE LOGITS
    iyi
    1.62
    rů
    1.57
     visibility
    1.53
     resaltar
    1.53
    ństw
    1.52
     speci
    1.52
    dje
    1.50
     aclarar
    1.49
    říve
    1.49
     respirar
    1.48
    Activations Density 0.002%

    No Known Activations