© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1466
    Prev
    Next
    INDEX
    Explanations

    This neuron flags non-English (foreign‐language) subword 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_24_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
     rétrécies
    0.62
    /
    0.57
     diabetics
    0.55
     triglycerides
    0.54
    ()/
    0.52
     noires
    0.52
     ofthe
    0.52
     imong
    0.50
     neuropathy
    0.50
    ־
    0.50
    POSITIVE LOGITS
    นี้
    0.66
     Moż
    0.63
     It
    0.62
     Have
    0.62
    め
    0.60
    とい
    0.59
    ッと
    0.59
     Let
    0.58
     Don
    0.57
     Há
    0.57
    Activations Density 0.000%

    No Known Activations