© 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. 1892
    Prev
    Next
    INDEX
    Explanations

    special characters and various languages

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

    This neuron is highly sensitive to Dutch-language subwords (i.e. tokens from Dutch words).

    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
    ุ่น
    0.54
    ᅬ
    0.52
    зиден
    0.48
     основании
    0.48
     Steele
    0.48
     असून
    0.47
    arrivée
    0.47
     చేరు
    0.46
    加え
    0.46
     catt
    0.45
    POSITIVE LOGITS
    citation
    0.56
     ジャン
    0.55
     अम्ल
    0.52
     ज़
    0.48
    Citation
    0.47
    zzz
    0.47
    their
    0.46
     строка
    0.46
     stanza
    0.46
     उनकी
    0.46
    Activations Density 0.084%

    No Known Activations