© 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. 16-GEMMASCOPE-2-RES-262K
    7. 28597
    Prev
    Next
    INDEX
    Explanations

    countably infinite or finite

    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_16_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
    ก
    0.53
    гол
    0.46
     Ć
    0.46
    াই
    0.45
    bés
    0.45
    กรา
    0.45
     LAS
    0.45
     classics
    0.44
     Ð
    0.43
    ক
    0.43
    POSITIVE LOGITS
    岕
    0.55
     progeny
    0.52
    行
    0.50
     subgroups
    0.47
    ",
    0.45
     सूत्रकृमि
    0.45
    Makefile
    0.44
    ζει
    0.44
    製品
    0.44
     عضو
    0.44
    Activations Density 0.001%

    No Known Activations