© 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. 34-GEMMASCOPE-RES-131K
    7. 79211
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns before lawyers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     추가
    -0.90
     badan
    -0.86
     FILLER
    -0.85
     treff
    -0.83
     passen
    -0.81
    htub
    -0.80
    vou
    -0.79
     páss
    -0.79
    ctical
    -0.78
     gemis
    -0.78
    POSITIVE LOGITS
     lawyers
    5.28
     lawyer
    5.22
     attorneys
    4.59
     attorney
    4.59
    lawyer
    3.56
     Lawyer
    3.36
     Lawyers
    3.30
    Lawyer
    3.17
    律师
    3.11
    弁護士
    2.78
    Activations Density 0.072%

    No Known Activations