© 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. 98234
    Prev
    Next
    INDEX
    Explanations

    programming exceptions and errors

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

    This neuron flags occurrences of exception-related identifiers (the word “Exception” and exception class definitions) in PHP code.

    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
     eros
    -0.84
    cellent
    -0.84
    urope
    -0.81
     obicei
    -0.81
     sezione
    -0.81
     armazenamento
    -0.79
    ᆷ
    -0.79
     emol
    -0.78
    poir
    -0.78
    ificent
    -0.78
    POSITIVE LOGITS
     exceptions
    1.62
     exception
    1.59
    exception
    1.27
    exceptions
    1.25
     Exception
    1.19
     Exceptions
    1.16
    EXCEPTION
    0.96
    例外
    0.95
     excepción
    0.94
    Exceptions
    0.94
    Activations Density 0.009%

    No Known Activations