© 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. 123998
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by nouns

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

    The neuron fires on possessive pronouns (especially “your” and “their”) that mark an audience or subjects’ ownership.

    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
     only
    -1.73
    峯
    -1.72
    𝟏
    -1.65
     sophisticated
    -1.62
     unusually
    -1.60
     extraordinarily
    -1.59
     supremely
    -1.58
     extravagant
    -1.57
     superbly
    -1.55
     intense
    -1.52
    POSITIVE LOGITS
    ing
    1.74
     mwaka
    1.66
     笑顔
    1.55
     pueda
    1.52
    s
    1.48
     stammen
    1.48
    莇
    1.45
     utafiti
    1.44
    m
    1.43
    >
    1.42
    Activations Density 0.023%

    No Known Activations