© 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. 8647
    Prev
    Next
    INDEX
    Explanations

    variable assignment or definition

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

    The neuron fires on semantically important content words (key nouns and verbs) rather than on common 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
    ל
    0.94
    癌症
    0.90
     producteurs
    0.88
    ल
    0.88
    lonitrile
    0.86
     radiotherapy
    0.86
     biopsies
    0.86
     emperors
    0.86
     dopamine
    0.85
     plastique
    0.85
    POSITIVE LOGITS
    ประจำ
    0.86
     pary
    0.75
    ﺎ
    0.75
    ->
    0.75
    ,
    0.74
    (),
    0.71
    ิจ
    0.71
     обязан
    0.68
     অভিজ্ঞ
    0.67
    parte
    0.66
    Activations Density 0.000%

    No Known Activations