© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12193
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron flags content-bearing “keyword” tokens—nouns, verbs, and technical terms—rather than function 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
    t
    0.79
    _)
    0.78
    ت
    0.77
    вез
    0.76
    groomed
    0.73
    _-
    0.73
    dets
    0.71
    Ass
    0.71
    Cat
    0.71
    sau
    0.71
    POSITIVE LOGITS
    ร่างกาย
    0.94
     maksymal
    0.88
    是没有
    0.88
     coba
    0.87
     fotografías
    0.85
     keltiradi
    0.81
     mascota
    0.81
     konsumen
    0.81
    唒
    0.80
     activación
    0.80
    Activations Density 0.000%

    No Known Activations