© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12208
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns/actions

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

    The neuron selectively activates on third-person singular possessive pronouns (e.g. its, her, his).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    possessive pronouns and determiners, particularly "its", "their", "his", "her", and "your".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    expressions of possession or ownership, including genitive markers like ’s and possessive pronouns.

    oai_token-act-pair · gpt-5Triggered 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
    Dix
    0.72
     kullanarak
    0.69
    SFR
    0.68
    אַ
    0.66
    Your
    0.64
    送料無料
    0.63
     sizin
    0.61
     unwitting
    0.61
    TUN
    0.61
     통해
    0.60
    POSITIVE LOGITS
     setiap
    0.81
    另一
    0.79
     another
    0.74
     Whatsapp
    0.73
     yester
    0.73
    每一个
    0.71
     whatsapp
    0.71
     beberapa
    0.70
     candidature
    0.70
     sufferings
    0.70
    Activations Density 0.227%

    No Known Activations