© 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. 22-GEMMASCOPE-RES-131K
    7. 32759
    Prev
    Next
    INDEX
    Explanations

    position: relative;

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    -1.34
     piemē
    -1.30
     této
    -1.30
     izman
    -1.23
     verwal
    -1.20
     from
    -1.18
     Feuchtigkeit
    -1.13
     chosen
    -1.12
     or
    -1.10
     auswählen
    -1.09
    POSITIVE LOGITS
     Kluwer
    1.03
    χε
    1.03
    nloa
    1.02
     romano
    0.98
     Sør
    0.97
    遽
    0.96
    šem
    0.94
    とその
    0.93
    Хотя
    0.93
    Tú
    0.91
    Activations Density 0.002%

    No Known Activations