© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25575
    Prev
    Next
    INDEX
    Explanations

    catch followed by parenthesis

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

    This neuron detects exception‐handling keywords (e.g. “catch” or “except”) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     semelh
    -1.29
     mangá
    -1.20
     procedimento
    -1.19
     consentimento
    -1.15
     such
    -1.11
     teka
    -1.10
     terce
    -1.09
     GRATU
    -1.09
     pensamento
    -1.09
     incorpora
    -1.07
    POSITIVE LOGITS
     it
    1.20
     what
    1.12
     or
    1.03
    本质
    1.00
     fühlte
    0.96
    níci
    0.94
     серьез
    0.94
    法则
    0.94
     they
    0.93
     as
    0.91
    Activations Density 0.000%

    No Known Activations