© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8244
    Prev
    Next
    INDEX
    Explanations

    common Dutch words

    np_acts-logits-general · gemini-2.5-flash-lite

    mensen, tussen, mensen, samen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     может
    0.67
    ті
    0.66
     возра
    0.64
    ль
    0.64
    є
    0.63
    с
    0.63
     сих
    0.62
    м
    0.61
     я
    0.60
     დღ
    0.60
    POSITIVE LOGITS
     onder
    1.32
     wanneer
    1.25
     onderzoek
    1.23
     voor
    1.22
     vijf
    1.21
     aan
    1.20
     welke
    1.20
     gebruik
    1.19
     Amerikaanse
    1.19
     een
    1.18
    Activations Density 0.015%

    No Known Activations