© 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. 10-GEMMASCOPE-RES-131K
    7. 45019
    Prev
    Next
    INDEX
    Explanations

    new object creation

    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_10/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
     of
    -1.80
     then
    -1.56
     dann
    -1.52
     én
    -1.47
     wilde
    -1.44
     enam
    -1.39
     lage
    -1.39
     roux
    -1.31
     moderne
    -1.31
     absolut
    -1.30
    POSITIVE LOGITS
     thing
    1.54
     kleineren
    1.53
     zweifel
    1.52
    hasilkan
    1.48
    在庫
    1.46
     humilde
    1.45
     generaciones
    1.43
     schonmal
    1.41
     quelconque
    1.41
     fruto
    1.41
    Activations Density 0.006%

    No Known Activations