© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 4162
    Prev
    Next
    INDEX
    Explanations

    NBA and world champions

    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_53_width_262k_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
     रिश्वत
    0.41
    ㄞ
    0.41
    মেঘ
    0.39
     ಕುಟ
    0.39
    庖
    0.39
     মূল্যা
    0.38
    BSData
    0.38
     concess
    0.38
     acúst
    0.38
    
    0.38
    POSITIVE LOGITS
     champion
    3.64
     champions
    3.47
    champion
    3.41
     Champion
    3.36
    Champion
    3.36
     championship
    3.19
     champ
    3.14
     CHAMP
    2.98
    冠军
    2.94
     চ্যাম্প
    2.92
    Activations Density 0.023%

    No Known Activations