© 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. 6136
    Prev
    Next
    INDEX
    Explanations

    possessive female pronoun

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

    The neuron strongly activates on words that describe someone’s internal sensations or emotional/physical states (e.g. confusion, searching, aching, peppering with questions).

    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
    k
    1.13
    meters
    1.05
    mg
    1.02
    V
    0.99
    ください
    0.98
     
    0.94
    yl
    0.93
    EF
    0.91
    map
    0.91
    ب
    0.91
    POSITIVE LOGITS
     própria
    1.01
     자신이
    0.97
     propias
    0.95
    ло
    0.93
     propia
    0.91
     stessa
    0.90
     собстве
    0.89
    欲望
    0.88
     universitaria
    0.87
    কা
    0.86
    Activations Density 0.013%

    No Known Activations