© 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. 34-GEMMASCOPE-RES-131K
    7. 117000
    Prev
    Next
    INDEX
    Explanations

    programming exceptions

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

    The neuron flags exception‐handling tokens (e.g. “throws” and “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_34/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
     innovation
    -0.96
     have
    -0.89
     neither
    -0.89
    先は
    -0.85
     field
    -0.83
    accoon
    -0.82
    erati
    -0.81
     goods
    -0.81
    產業
    -0.80
     řízení
    -0.80
    POSITIVE LOGITS
     Teller
    0.91
    exceptions
    0.91
    ктей
    0.89
     exceptions
    0.86
    gk
    0.84
    matician
    0.83
    muje
    0.82
     System
    0.82
    лке
    0.80
    ApiException
    0.79
    Activations Density 0.003%

    No Known Activations