© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54682
    Prev
    Next
    INDEX
    Explanations

    calculate pot odds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bluff
    0.63
     bluff
    0.62
     poker
    0.56
    賭
    0.47
    uatu
    0.46
    raising
    0.44
     europa
    0.44
    赌
    0.43
     betting
    0.42
     покер
    0.42
    POSITIVE LOGITS
    陶瓷
    0.43
     керами
    0.43
     Premio
    0.41
     प्रहरी
    0.40
    享有
    0.39
     ceramic
    0.38
    Cara
    0.38
     контей
    0.38
    Rap
    0.38
     ceramics
    0.37
    Activations Density 0.010%

    No Known Activations