© 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. 68641
    Prev
    Next
    INDEX
    Explanations

    practical use applications

    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
     yaklaşık
    -2.34
     Then
    -2.20
     mehreren
    -2.17
     startling
    -2.14
    )-
    -2.06
    %,
    -2.06
    am
    -2.05
     ۵
    -2.02
     Our
    -1.99
     dando
    -1.97
    POSITIVE LOGITS
    𓆉
    2.83
    衕
    2.80
    this
    2.66
    鉺
    2.50
    𓆜
    2.47
    酲
    2.42
    アプリケーション
    2.39
    ﮨ
    2.39
     antwortete
    2.36
    ﱠ
    2.31
    Activations Density 0.001%

    No Known Activations