© 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. 10-GEMMASCOPE-RES-131K
    7. 71274
    Prev
    Next
    INDEX
    Explanations

    exception class names

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

    The neuron activates on the appearance of exception class names or the token “Exception” in 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_10/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
     That
    -2.00
     annan
    -1.94
     Didn
    -1.88
     plagued
    -1.86
    z
    -1.83
    a
    -1.78
    蕻
    -1.77
    zembro
    -1.77
    This
    -1.77
     activa
    -1.74
    POSITIVE LOGITS
    .
    2.06
     buurt
    2.02
    馐
    2.00
    鲩
    1.86
     اذا
    1.84
     terwijl
    1.83
    珝
    1.81
    $("
    1.80
    葑
    1.80
     ttc
    1.77
    Activations Density 0.006%

    No Known Activations