© 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. 116864
    Prev
    Next
    INDEX
    Explanations

    exception

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

    This neuron strongly responds to occurrences of “exception” (especially in phrases like “the exception,” “no exception,” or “notable exception”) indicating an exception to a rule.

    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
    âteaux
    -0.84
    ㄈ
    -0.80
     ../../
    -0.79
    tava
    -0.77
    łaści
    -0.77
     semblent
    -0.77
    ">+
    -0.75
    ěk
    -0.73
    (/[
    -0.73
    ଼
    -0.73
    POSITIVE LOGITS
     exception
    7.78
     exceptions
    7.78
     Exceptions
    6.09
    exceptions
    5.84
    Exceptions
    5.56
    exception
    5.31
    例外
    5.19
     Exception
    5.03
     excepción
    4.81
    Exception
    4.75
    Activations Density 0.097%

    No Known Activations