© 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. 31-GEMMASCOPE-2-RES-262K
    7. 141208
    Prev
    Next
    INDEX
    Explanations

    mafia, gangsters, and Italian/Sicilian figures

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

    gangster, mafia, crime families

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Mn
    0.47
     eLearning
    0.47
     SAIL
    0.46
     pédagog
    0.45
     Science
    0.45
     Shuttle
    0.45
     संस्कृत
    0.44
    ettre
    0.44
     algal
    0.44
     झ
    0.44
    POSITIVE LOGITS
     gangster
    1.16
     gangsters
    1.08
     गैंगस्टर
    1.06
     Mafia
    0.95
     mafia
    0.95
     underworld
    0.82
     माफिया
    0.76
     gamblers
    0.72
    赌场
    0.72
     Godfather
    0.70
    Activations Density 0.278%

    No Known Activations