© 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. 11111
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by body parts

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

    The neuron fires on possessive constructions describing characters’ bodies—e.g. “his arm,” “my hands,” “her shoulders”—so it’s spotting mentions of body parts framed by “my,” “his,” or “her.”

    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
    ホームページ
    0.73
     gelişmeler
    0.64
    HAN
    0.63
     любых
    0.61
    榻
    0.61
     récord
    0.60
     razvoja
    0.59
     Developments
    0.58
     pokrač
    0.58
     développement
    0.57
    POSITIVE LOGITS
     fingers
    0.77
     thighs
    0.76
     lips
    0.70
     arms
    0.68
     wrists
    0.68
     fingertips
    0.67
    嘴
    0.63
     cheeks
    0.63
     fists
    0.62
     sides
    0.61
    Activations Density 0.029%

    No Known Activations