© 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. 34-GEMMASCOPE-RES-131K
    7. 91156
    Prev
    Next
    INDEX
    Explanations

    exceptions and throwing them

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

    The neuron detects mentions of exceptions (i.e. the token “exception” and related error-reporting terms) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     yetu
    -0.77
     obicei
    -0.73
     berechnet
    -0.73
    █
    -0.73
    ragt
    -0.72
     لذا
    -0.72
    RESOLVED
    -0.71
    Gy
    -0.70
    WarningLevel
    -0.69
     diffus
    -0.69
    POSITIVE LOGITS
     throw
    4.03
     throws
    3.75
     throwing
    3.67
     thrown
    3.56
    throw
    3.45
     threw
    3.44
     exception
    3.27
     Throw
    3.25
    throws
    3.14
     exceptions
    3.08
    Activations Density 0.193%

    No Known Activations