© 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. 91227
    Prev
    Next
    INDEX
    Explanations

    methods that throw exceptions

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

    This neuron activates on Java method signatures that declare exceptions (the “throws” keyword).

    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
     มาก
    -1.24
     JAXBElement
    -1.21
    Анти
    -1.18
     fà
    -1.14
    它的
    -1.13
     svůj
    -1.09
     wybrać
    -1.07
     scow
    -1.06
     périph
    -1.05
     Vorte
    -1.05
    POSITIVE LOGITS
     Exception
    1.70
     so
    1.30
     exceptions
    1.22
    Exception
    1.21
     gick
    1.16
    exceptions
    1.14
     exception
    1.10
     or
    1.09
    ような
    1.04
     IOException
    1.02
    Activations Density 0.001%

    No Known Activations