© 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. 828
    Prev
    Next
    INDEX
    Explanations

    academic, supervision

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

    The neuron fires on non-English (foreign-language) tokens.

    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
    utiliser
    0.77
    kový
    0.76
     भेड़
    0.76
    ickeys
    0.75
    爣
    0.75
    ubuk
    0.73
    lerimiz
    0.71
     लीवर
    0.70
    णारे
    0.70
    处理器
    0.70
    POSITIVE LOGITS
     (!
    0.66
     (
    0.63
     .
    0.63
     –
    0.63
     (...)
    0.61
     ,
    0.60
    ฯ
    0.59
     [
    0.58
    0.57
    .,
    0.56
    Activations Density 0.047%

    No Known Activations