© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34718
    Prev
    Next
    INDEX
    Explanations

    types or errors encountered

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

    This neuron detects error‐handling and exception‐related tokens (e.g. raising or formatting error messages and exception names).

    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
     after
    -1.08
     more
    -0.99
    robin
    -0.92
     Gleichzeitig
    -0.91
    janya
    -0.88
     fairer
    -0.88
     SALUD
    -0.86
    iciado
    -0.85
     three
    -0.85
    し
    -0.85
    POSITIVE LOGITS
     types
    1.20
     incompatible
    1.14
     unsuitable
    1.11
    类型
    1.05
    unexpected
    1.02
     into
    1.00
     devrait
    1.00
    TypeService
    0.98
     typeof
    0.98
     isinstance
    0.98
    Activations Density 0.018%

    No Known Activations