© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 5355
    Prev
    Next
    INDEX
    Explanations

    playoff stages

    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
    Negative Logits
    ្នាំ
    0.61
     উপাদান
    0.59
    ម្លៃ
    0.59
     discontinuities
    0.56
    យៈ
    0.54
    ائص
    0.54
    িল্প
    0.52
     carène
    0.52
    ㇂
    0.52
    ាតុ
    0.52
    POSITIVE LOGITS
     playoff
    1.48
     playoffs
    1.33
     Playoffs
    1.29
     Finals
    1.26
     semifinals
    1.20
     finalists
    1.18
     finals
    1.16
     semifinal
    1.16
     सेमीफाइनल
    1.14
     quarterfinals
    1.13
    Activations Density 0.005%

    No Known Activations