© 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. 31-GEMMASCOPE-2-RES-16K
    7. 517
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

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

    The neuron is keyed to first-person pronouns and possessive adjectives (e.g. “our,” “my,” “I”) indicating self-referential language.

    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_31_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
     Trên
    0.44
     ();
    0.41
     不是
    0.39
    ）
    0.39
    Tiene
    0.38
    C
    0.38
     문제는
    0.38
     ())
    0.37
     Tanık
    0.37
     [{
    0.37
    POSITIVE LOGITS
     own
    1.23
     propias
    0.93
     propios
    0.89
     própria
    0.86
     eigenen
    0.85
     próprias
    0.84
     propia
    0.81
     propres
    0.81
     próprios
    0.80
     OWN
    0.79
    Activations Density 0.925%

    No Known Activations