© 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. 75025
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns in several languages

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

    This neuron activates on first-person possessive pronouns (e.g. “my,” “our,” etc.) across different languages.

    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
     Verhandlungen
    -2.77
    蠵
    -2.72
    謦
    -2.67
    BIÉN
    -2.53
    ついで
    -2.48
    
    -2.42
     эти
    -2.41
    \%,
    -2.39
    等我
    -2.34
    ه‌ای
    -2.30
    POSITIVE LOGITS
     ‘‘
    2.78
    。「
    2.36
     штука
    2.23
    1
    2.20
    </h1>
    2.17
    The
    2.11
    ,
    2.06
    珦
    2.06
    و
    2.06
    เกง
    2.05
    Activations Density 0.001%

    No Known Activations