© 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. 32901
    Prev
    Next
    INDEX
    Explanations

    exception handling

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

    The neuron activates strongly on “catch (Exception …)” sequences, i.e. exception‐handling clauses.

    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
     doivent
    -0.80
    ipot
    -0.80
     시간
    -0.79
    Important
    -0.77
     cią
    -0.77
     décidé
    -0.76
    violi
    -0.76
    癞
    -0.75
    法律
    -0.75
    のだろう
    -0.74
    POSITIVE LOGITS
     ex
    1.30
    )
    1.07
     EX
    1.05
    ex
    1.03
    )
    1.02
    ÉM
    0.99
     Exception
    0.92
     exception
    0.90
    ielles
    0.88
     Ex
    0.88
    Activations Density 0.003%

    No Known Activations