© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127943
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and personal pronouns

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

    The neuron is primarily detecting personal pronouns (e.g. “their,” “you,” “his”).

    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
    ↵↵
    -1.68
    \
    -1.62
     vanligt
    -1.55
    ٦
    -1.55
     coreana
    -1.52
     The
    -1.51
     olika
    -1.50
     naturels
    -1.50
     санкт
    -1.48
     oscura
    -1.48
    POSITIVE LOGITS
    cenzo
    1.98
     comentário
    1.95
     svolta
    1.71
    の概要
    1.70
    dhury
    1.69
    を買う
    1.66
    はこちらから
    1.66
    dalena
    1.65
     estúdio
    1.64
    inetic
    1.63
    Activations Density 0.004%

    No Known Activations