© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83842
    Prev
    Next
    INDEX
    Explanations

    pronouns: us, them, their, its

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

    This neuron activates on group-referencing pronouns and words (e.g. “us,” “we,” “them,” “they,” “all,” “group”) that mark in-group versus out-group distinctions.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     himself
    -1.24
    ponenten
    -1.23
    шим
    -1.19
     Tons
    -1.16
    شناسی
    -1.16
     Championnat
    -1.15
     зиму
    -1.14
     خودش
    -1.13
     prata
    -1.12
    Some
    -1.11
    POSITIVE LOGITS
     its
    1.52
     adecuados
    1.23
     vykon
    1.23
    conector
    1.21
     execução
    1.20
     masculinos
    1.20
     čier
    1.19
     všet
    1.16
     realize
    1.12
     rých
    1.12
    Activations Density 0.069%

    No Known Activations