© 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. 82451
    Prev
    Next
    INDEX
    Explanations

    java.lang exceptions

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

    This neuron detects fragments of Java exception stack traces (e.g. the “java.lang…” error lines and related tokens).

    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
    ジュアル
    -0.80
     نی
    -0.80
    SET
    -0.77
    Prepared
    -0.72
    🟨
    -0.71
    D
    -0.69
    GetError
    -0.69
    Topic
    -0.68
    Map
    -0.68
    ated
    -0.66
    POSITIVE LOGITS
     Runtime
    1.98
    Throwable
    1.41
     Throwable
    1.28
     IllegalArgument
    1.25
     Number
    1.19
    Runtime
    1.19
    NumberFormat
    1.19
     Exception
    1.13
     Class
    1.10
    RuntimeException
    1.09
    Activations Density 0.057%

    No Known Activations