© 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. 108791
    Prev
    Next
    INDEX
    Explanations

    blackjack

    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
    Ré
    -0.75
    眶
    -0.75
     Clap
    -0.74
     Unilever
    -0.73
    荐
    -0.71
     飾
    -0.70
     Tundra
    -0.68
     fauna
    -0.68
    spora
    -0.68
    আ
    -0.67
    POSITIVE LOGITS
     blackjack
    1.46
     bust
    1.45
    Bust
    1.41
    bust
    1.37
     Blackjack
    1.34
     Bust
    1.27
     busts
    1.18
     BLACK
    1.13
     Black
    1.05
     BJ
    1.05
    Activations Density 0.010%

    No Known Activations