© 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. 41-GEMMASCOPE-2-RES-262K
    7. 100956
    Prev
    Next
    INDEX
    Explanations

    running

    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_all/layer_41_width_262k_l0_big
    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
     सामना
    0.38
     તૈય
    0.35
    лган
    0.35
    Adjacent
    0.35
     Adjacent
    0.35
    ඳ
    0.35
     leaned
    0.34
    යක
    0.34
    हाई
    0.34
    蛎
    0.33
    POSITIVE LOGITS
     running
    1.45
    วิ่ง
    1.37
    跑
    1.35
    running
    1.33
     chạy
    1.30
     Running
    1.28
    Running
    1.27
     run
    1.19
     RUN
    1.19
     roaming
    1.16
    Activations Density 0.001%

    No Known Activations