© 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. 12203
    Prev
    Next
    INDEX
    Explanations

    try-catch-finally blocks

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

    the keyword "catch" in exception handling blocks in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on exception‐handling keywords (especially “catch” and related blocks) 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_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
    これは
    -1.61
     AspNetCore
    -1.35
     exemplu
    -1.34
     hemd
    -1.34
     concurrently
    -1.33
    this
    -1.32
     wast
    -1.32
     preced
    -1.31
    </h1>
    -1.30
     exemplified
    -1.30
    POSITIVE LOGITS
    uable
    1.50
     umiejęt
    1.48
    ifiable
    1.48
    顏色
    1.46
     pozycji
    1.43
    ("}\
    1.43
    寕
    1.43
     wiggle
    1.40
    ++)
    1.38
    kumar
    1.38
    Activations Density 0.001%

    No Known Activations