© 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. 9594
    Prev
    Next
    INDEX
    Explanations

    NotFoundError

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

    The neuron fires on mentions of exception or error types (e.g., “IOException,” “NameNotFoundException,” “CacheException,” etc.) in technical/log text.

    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
    <unused58>
    0.59
    ად
    0.54
     inferiority
    0.53
     unauthorized
    0.52
     unreasonable
    0.51
     desarrollada
    0.51
    кинуло
    0.51
     दुकानों
    0.50
     ሚ
    0.50
    руют
    0.49
    POSITIVE LOGITS
    ::~
    0.59
     Ember
    0.58
     Larsen
    0.57
    uchen
    0.56
     Sind
    0.56
    Translation
    0.55
     Shen
    0.54
     Karo
    0.54
     Lion
    0.53
     Ida
    0.53
    Activations Density 0.000%

    No Known Activations