© 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. 98696
    Prev
    Next
    INDEX
    Explanations

    foreign names and places

    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
    𝟐
    -1.57
     if
    -1.46
     because
    -1.44
     it
    -1.42
    there
    -1.39
     rocher
    -1.38
    тку
    -1.38
    ⌄
    -1.36
     forro
    -1.34
     ваз
    -1.31
    POSITIVE LOGITS
    0
    1.57
     immense
    1.48
     żad
    1.45
     example
    1.42
     tamamen
    1.41
     nhưng
    1.38
     genellikle
    1.38
     Können
    1.38
     Besonder
    1.37
     Chủ
    1.35
    Activations Density 0.039%

    No Known Activations