© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8260
    Prev
    Next
    INDEX
    Explanations

    social connection and people

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

    social connection and friendships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ancestor
    0.46
     બાળક
    0.45
     recipient
    0.43
     defendant
    0.41
     pupil
    0.41
    defendant
    0.40
    Defendant
    0.40
     employee
    0.39
     үшін
    0.39
    銜
    0.39
    POSITIVE LOGITS
     fellow
    1.03
     compañeros
    0.89
     kindred
    0.88
    fellow
    0.88
     camaraderie
    0.84
     friendly
    0.82
     peers
    0.78
     ludzi
    0.77
     людей
    0.77
     oameni
    0.77
    Activations Density 0.675%

    No Known Activations