© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20763
    Prev
    Next
    INDEX
    Explanations

    exception handling

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

    The neuron is spotting exception‐handling constructs (e.g. “try”, “catch”, “catch (Exception)”).

    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
    maining
    -1.43
    lıyor
    -1.19
     られる
    -1.19
     насеља
    -1.16
     their
    -1.14
     Estamos
    -1.10
     holdt
    -1.10
     ТАК
    -1.09
     Otros
    -1.09
    hehe
    -1.09
    POSITIVE LOGITS
     if
    1.69
    if
    1.35
     прибли
    1.09
    १
    1.09
    ínica
    1.07
    та
    1.05
     ponieważ
    1.05
    inescent
    1.05
     paio
    1.05
     than
    1.04
    Activations Density 1.554%

    No Known Activations