© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11372
    Prev
    Next
    INDEX
    Explanations

    0 to 100

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

    This neuron detects numeric reference markers and bibliographic numbers (e.g. years, volume/issue/page numbers) in academic citations.

    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
    plants
    0.75
    لل
    0.75
    ل
    0.75
    ط
    0.74
    مد
    0.71
    م
    0.71
    ئ
    0.70
     হইতেছিল
    0.70
    د
    0.66
    Et
    0.63
    POSITIVE LOGITS
    ской
    1.13
     fútbol
    1.07
    ский
    1.02
     канторы
    1.00
     perinatal
    0.97
     hedon
    0.96
    uscular
    0.94
     optomet
    0.92
     szpital
    0.91
     telehealth
    0.91
    Activations Density 0.000%

    No Known Activations