© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103951
    Prev
    Next
    INDEX
    Explanations

    Java exceptions

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

    The neuron detects mentions of exception or error type names (e.g. Java exception class identifiers).

    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
     through
    -1.05
     with
    -0.94
    NotFoundError
    -0.90
    bunya
    -0.88
    ).
    -0.87
     now
    -0.80
    jącym
    -0.79
     while
    -0.78
     three
    -0.78
     Cæ
    -0.77
    POSITIVE LOGITS
     exceptions
    2.17
     exception
    2.17
     Exception
    1.84
    Exception
    1.83
    exceptions
    1.79
     Exceptions
    1.70
    ruptedException
    1.69
     excepción
    1.66
    exception
    1.55
    Exceptions
    1.50
    Activations Density 0.014%

    No Known Activations