© 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. 6916
    Prev
    Next
    INDEX
    Explanations

    matrix algebra and calculus

    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
     یا
    -1.85
    umpulan
    -1.81
     kompatibel
    -1.74
    鷽
    -1.74
    まき
    -1.68
    以上です
    -1.61
    谭
    -1.61
     célé
    -1.60
    しました
    -1.60
    yczny
    -1.59
    POSITIVE LOGITS
    .
    2.44
     概要
    1.82
     have
    1.79
     to
    1.78
    ם
    1.71
    la
    1.71
    
    1.70
     メニュー
    1.67
    眼下
    1.67
    of
    1.64
    Activations Density 0.006%

    No Known Activations