© 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. 867
    Prev
    Next
    INDEX
    Explanations

    verbs for actions and states

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

    This neuron responds to foreign-language words or phrases—especially tokens containing non-English characters or diacritics.

    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
     mutta
    0.63
     видов
    0.60
     sideways
    0.60
     &/
    0.60
     tangents
    0.59
     intersections
    0.59
     resultant
    0.59
     diminishing
    0.58
    *;
    0.58
     policial
    0.57
    POSITIVE LOGITS
    ította
    0.70
    et
    0.65
    at
    0.64
    ကြ
    0.64
    ется
    0.61
    ジュ
    0.61
    ます
    0.60
     też
    0.59
    は
    0.59
    en
    0.58
    Activations Density 0.000%

    No Known Activations