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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65142
    Prev
    Next
    INDEX
    Explanations

    gambling and lotteries

    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
     yahoo
    -0.80
    рованию
    -0.79
     வெ
    -0.74
    cheidung
    -0.72
    frutar
    -0.70
     virulent
    -0.69
     ferro
    -0.68
    TestBase
    -0.68
     உ
    -0.67
     CUDA
    -0.67
    POSITIVE LOGITS
     retailers
    1.20
     retailer
    1.19
     players
    1.09
     player
    1.09
     terminals
    1.02
    Players
    0.99
     Retailers
    0.96
     terminal
    0.95
     Retailer
    0.94
    Retail
    0.92
    Activations Density 0.009%

    No Known Activations