© 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. 22-GEMMASCOPE-RES-131K
    7. 32669
    Prev
    Next
    INDEX
    Explanations

    particular groups of people

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    貴重な
    -0.96
    大切
    -0.95
    評判
    -0.94
     deines
    -0.94
    谆
    -0.93
    utate
    -0.92
    してた
    -0.92
    アイデア
    -0.92
    ственная
    -0.91
     íntegra
    -0.91
    POSITIVE LOGITS
     people
    1.57
     young
    1.46
     staff
    1.34
     students
    1.19
     customers
    1.16
     patients
    1.13
     everyone
    1.13
     companies
    1.12
    Décès
    1.11
    dekor
    1.11
    Activations Density 0.097%

    No Known Activations