© 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. 83926
    Prev
    Next
    INDEX
    Explanations

    features, functions, or capabilities

    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
     it
    -2.64
     our
    -1.60
    0
    -1.56
     there
    -1.54
    啊啊
    -1.47
     probablemente
    -1.46
     trattano
    -1.45
    了一口
    -1.40
    มัน
    -1.36
    枚目
    -1.35
    POSITIVE LOGITS
    erdings
    1.49
    entown
    1.45
     paragraphe
    1.41
    しみ
    1.39
    stalgia
    1.39
    emore
    1.34
     کنید
    1.33
     ナイロン
    1.32
    ͇
    1.31
     Citroën
    1.30
    Activations Density 0.169%

    No Known Activations