© 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. 73561
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.49
     government
    -1.28
     in
    -1.27
     other
    -1.23
     You
    -1.20
     over
    -1.18
     If
    -1.17
     similar
    -1.17
     this
    -1.16
     necesariamente
    -1.10
    POSITIVE LOGITS
     fatale
    1.38
     conster
    1.36
     sentral
    1.34
     fufficient
    1.34
     lenge
    1.30
     tille
    1.30
     brune
    1.30
     Pria
    1.29
     jule
    1.27
     interieur
    1.26
    Activations Density 0.051%

    No Known Activations