© 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. 85467
    Prev
    Next
    INDEX
    Explanations

    Names and East Asian places/concepts, especially with "Yu"

    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
    ing
    1.46
    is
    1.45
    は
    1.32
    是
    1.27
    ن
    1.20
    ン
    1.16
    en
    1.15
    िंग
    1.15
    కు
    1.13
    은
    1.09
    POSITIVE LOGITS
     Yu
    1.34
     yu
    1.27
    $.
    1.22
    ל
    1.22
    ר
    1.16
    ции
    1.13
     swarm
    1.05
    л
    1.05
    Yu
    1.05
    \%)
    1.02
    Activations Density 0.001%

    No Known Activations