© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38571
    Prev
    Next
    INDEX
    Explanations

    score difference or margin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    r
    -1.57
    ,\\
    -1.46
    意味着
    -1.38
    亚马逊
    -1.29
    6
    -1.27
     ちゃん
    -1.24
     вони
    -1.23
     дітей
    -1.23
    丫头
    -1.22
    售价
    -1.22
    POSITIVE LOGITS
     only
    1.69
     étaient
    1.46
    他能
    1.40
    breviations
    1.34
     furent
    1.31
     without
    1.29
    дости
    1.29
     ۱۵
    1.28
     However
    1.27
     atriz
    1.27
    Activations Density 0.010%

    No Known Activations