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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67512
    Prev
    Next
    INDEX
    Explanations

    tennis scores

    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
     siè
    -1.72
     rése
    -1.56
     piaci
    -1.48
     mépris
    -1.48
     pérd
    -1.47
     laine
    -1.47
     perles
    -1.46
     bottes
    -1.44
     favoris
    -1.44
     praktis
    -1.44
    POSITIVE LOGITS
     J
    1.37
     also
    1.33
     D
    1.33
     a
    1.28
     Y
    1.27
     F
    1.23
     M
    1.23
    :
    1.22
    …
    1.21
    er
    1.18
    Activations Density 0.003%

    No Known Activations