© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72755
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

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

    The neuron is triggered by the second-person possessive determiner “your.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -1.78
    4
    -1.63
     using
    -1.54
     use
    -1.48
    X
    -1.45
    6
    -1.43
     making
    -1.43
     зробити
    -1.41
     have
    -1.39
     give
    -1.37
    POSITIVE LOGITS
     ส์
    1.59
    絝
    1.57
    ⬈
    1.51
    쫀
    1.48
     histó
    1.48
    穑
    1.43
    راهن
    1.42
     Schuhe
    1.40
    ญี่ป
    1.40
    剛好
    1.40
    Activations Density 0.009%

    No Known Activations