© 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. 58034
    Prev
    Next
    INDEX
    Explanations

    proper names and foreign terms

    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
     één
    -1.53
    0
    -1.46
    1
    -1.43
     have
    -1.41
     {},
    -1.30
     abbiamo
    -1.27
    рист
    -1.27
     Wachs
    -1.26
     problemet
    -1.25
    也没
    -1.23
    POSITIVE LOGITS
     damaged
    1.66
    鱻
    1.56
     notorious
    1.50
    rhosis
    1.49
     praktischen
    1.48
     that
    1.47
     Geduld
    1.47
    周泽
    1.45
    𖥧
    1.45
    鬈
    1.45
    Activations Density 0.009%

    No Known Activations