© 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. 820
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on non-English (non-ASCII) text—i.e. tokens written in other languages or scripts.

    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
     ஆனால்
    0.46
    一方で
    0.44
     чтобы
    0.44
    而且
    0.43
    Чтобы
    0.42
    而
    0.41
    此外
    0.41
    dengan
    0.40
    扨
    0.40
    ただし
    0.39
    POSITIVE LOGITS
     열심히
    0.50
     비롯
    0.48
     başlayan
    0.48
     쉽게
    0.46
     부터
    0.46
     익
    0.45
     발생하는
    0.45
     faç
    0.44
     쓸
    0.44
     yeniden
    0.44
    Activations Density 0.009%

    No Known Activations