© 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. 22-GEMMASCOPE-RES-131K
    7. 74877
    Prev
    Next
    INDEX
    Explanations

    exception handling or errors

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

    The neuron reliably lights up on code tokens involved in error or exception handling (e.g. Exception class names, “try,” “raise,” “get_object_or_404,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ἄ
    -1.11
     burch
    -1.08
    Biographical
    -1.02
     relatif
    -1.00
     ſp
    -0.97
     tebal
    -0.96
     ffilmiau
    -0.96
    
    -0.94
    wollen
    -0.94
     NEW
    -0.93
    POSITIVE LOGITS
    ּוֹ
    1.06
     has
    0.90
     존
    0.89
     bring
    0.88
    וֹ
    0.84
     preexisting
    0.80
     đủ
    0.79
    there
    0.79
    文化財
    0.78
     service
    0.77
    Activations Density 0.003%

    No Known Activations