© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128905
    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
     (
    -1.80
     A
    -1.68
     S
    -1.66
     one
    -1.65
     M
    -1.63
     in
    -1.62
     by
    -1.61
     most
    -1.59
     L
    -1.57
     R
    -1.56
    POSITIVE LOGITS
     içeris
    1.62
     étan
    1.61
     dingen
    1.55
     zacht
    1.55
     erbjuder
    1.52
     eenvoudig
    1.50
    ↵↵
    1.49
    "],
    1.48
     görüntüsü
    1.48
     variedade
    1.48
    Activations Density 0.011%

    No Known Activations