© 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. 22-GEMMASCOPE-RES-131K
    7. 68893
    Prev
    Next
    INDEX
    Explanations

    try...catch clauses

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

    The neuron strongly activates on the curly‐brace tokens (“{” and “}”) that delimit code blocks (especially around try/catch) in programming snippets.

    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
     this
    -1.09
    >(),
    -0.84
    findViewById
    -0.83
    льному
    -0.82
    を抜
    -0.81
    蛧
    -0.80
    𝗋
    -0.80
     ^=
    -0.80
     (*(
    -0.79
    {~
    -0.79
    POSITIVE LOGITS
     then
    1.27
    including
    0.94
     or
    0.90
    mények
    0.88
     następnie
    0.87
    ritation
    0.85
     stří
    0.82
    推特
    0.82
    лись
    0.81
     včetně
    0.81
    Activations Density 0.001%

    No Known Activations