© 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. 38695
    Prev
    Next
    INDEX
    Explanations

    logo and icon file paths

    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
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -1.57
     be
    -1.30
    either
    -1.27
    ⣥
    -1.25
    жду
    -1.24
     decât
    -1.24
    southeast
    -1.19
    اعده
    -1.18
     птицы
    -1.17
     !”
    -1.13
    POSITIVE LOGITS
     from
    1.74
     of
    1.62
    众多
    1.44
    ของ
    1.43
     dergleichen
    1.38
    当时的
    1.38
    どうして
    1.37
    当時は
    1.34
     nosso
    1.33
    おわりに
    1.32
    Activations Density 0.035%

    No Known Activations