© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 48659
    Prev
    Next
    INDEX
    Explanations

    the big question

    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
     Comparing
    0.38
     Duke
    0.37
    <em>
    0.37
     *
    0.36
     Thế
    0.35
     ਜਾਂ
    0.35
    Definitely
    0.35
     یا
    0.35
     Being
    0.34
     Manuel
    0.34
    POSITIVE LOGITS
     "]");
    0.38
    ../../../
    0.38
    锑
    0.37
     ষ্ট
    0.37
     conectado
    0.36
    ಂಟ
    0.35
     шесть
    0.35
     восем
    0.35
     لوی
    0.35
    গিরই
    0.35
    Activations Density 0.028%

    No Known Activations