© 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. 7182
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun 'their' and what follows

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

    This neuron detects instances of the possessive pronoun “their,” especially in organizational or business contexts.

    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
    是一個
    1.05
    是一个
    1.05
     Два
    0.97
    是个
    0.95
     two
    0.87
    你
    0.86
    你能
    0.85
    小子
    0.85
     двумя
    0.85
     ყველა
    0.85
    POSITIVE LOGITS
     themselves
    2.39
     leurs
    2.11
    their
    2.06
     their
    1.95
     ihre
    1.88
     Their
    1.85
    他們的
    1.85
    Their
    1.84
     ihren
    1.81
     તેમના
    1.80
    Activations Density 2.120%

    No Known Activations