© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1553
    Prev
    Next
    INDEX
    Explanations

    error handling

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

    The neuron is sensitive to numerical tokens (error codes, version numbers, file sizes, hex addresses, etc.) in technical/log output.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hemispheres
    0.69
     anga
    0.68
    तेक
    0.63
    invent
    0.57
    sunline
    0.56
    vamo
    0.56
     lhs
    0.56
    뤽
    0.56
    anagram
    0.55
    skyblue
    0.55
    POSITIVE LOGITS
     Error
    2.09
     error
    2.06
     errors
    2.02
     Errors
    1.98
     ERROR
    1.97
    Error
    1.92
    error
    1.91
     errores
    1.88
    错误
    1.87
     Fehler
    1.84
    Activations Density 0.096%

    No Known Activations