© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13652
    Prev
    Next
    INDEX
    Explanations

    Asciminib medications

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

    The neuron fires most strongly on semantically rich content words (not function words)—especially nouns, verbs, and proper nouns that carry topical meaning.

    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
     excit
    0.87
     nozzles
    0.84
    n
    0.82
     stanza
    0.79
    AF
    0.79
     isothermal
    0.79
    STRUCTIONS
    0.77
     scientists
    0.77
    EF
    0.77
     ambassador
    0.76
    POSITIVE LOGITS
    setVisibility
    0.73
     nudity
    0.71
    ⅾ
    0.70
     বদ
    0.69
    Дру
    0.69
    вне
    0.69
    ளவில்
    0.68
    спекти
    0.68
    льга
    0.68
    лід
    0.68
    Activations Density 0.000%

    No Known Activations