© 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. 45601
    Prev
    Next
    INDEX
    Explanations

    Luke Skywalker, Luke Combs, lukewarm

    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
    ಿಯಲ್ಲಿ
    0.45
    Supreme
    0.39
    branco
    0.38
    lü
    0.38
    Mask
    0.37
    Rest
    0.36
    ɣ
    0.36
    鹂
    0.36
    🏐
    0.36
     ಕನ್ನಡ
    0.36
    POSITIVE LOGITS
     luk
    0.70
     Luke
    0.69
     Luk
    0.67
     luke
    0.66
     Skywalker
    0.61
    Luke
    0.59
     warm
    0.53
    Luk
    0.53
    篁
    0.50
    asz
    0.47
    Activations Density 0.002%

    No Known Activations