© 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. 130924
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens involved in error handling or exception/reporting (e.g. throw, raise, panic, error messages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    error reporting keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     GRATU
    -1.06
     those
    -1.06
     also
    -1.04
     already
    -0.98
    という感じ
    -0.95
     智能
    -0.95
     whose
    -0.94
     may
    -0.94
    始めて
    -0.94
    umán
    -0.93
    POSITIVE LOGITS
    ござ
    0.95
    0.93
     conocida
    0.92
    ]<<
    0.90
    lendi
    0.88
     NotImplemented
    0.87
     traditionelle
    0.85
     tellement
    0.84
     flashlight
    0.84
     каждой
    0.84
    Activations Density 0.004%
    No Known Activations