© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109632
    Prev
    Next
    INDEX
    Explanations

    mafia, mob, and gangsters

    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
    đu
    -0.80
     señales
    -0.80
    ↔
    -0.78
     camping
    -0.77
    衛隊
    -0.75
    SaveChangesAsync
    -0.74
     najczęściej
    -0.74
     Dicapai
    -0.74
    Scopri
    -0.74
    Prezzo
    -0.74
    POSITIVE LOGITS
     underworld
    2.03
     mafia
    1.98
     Mafia
    1.87
     gangster
    1.84
     maf
    1.76
    Mafia
    1.66
     mob
    1.61
    mafia
    1.59
     gangsters
    1.56
     gang
    1.48
    Activations Density 0.067%

    No Known Activations