© 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. 10-GEMMASCOPE-RES-131K
    7. 12320
    Prev
    Next
    INDEX
    Explanations

    Exception keyword in code

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

    the word "Exception" in programming code, particularly in error handling contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    蕻
    -2.27
    ╽
    -2.09
     ,'
    -2.08
    鋱
    -2.08
    gunas
    -2.02
    
    -1.98
    tagHelper
    -1.95
    蟊
    -1.93
    」「
    -1.91
    
    -1.91
    POSITIVE LOGITS
    .
    3.52
    {
    2.83
    _
    2.38
    ↵↵
    2.22
     because
    2.19
    ,
    2.13
    0
    2.13
    What
    2.13
    <
    2.08
    8
    1.99
    Activations Density 0.005%

    No Known Activations