© 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. 67112
    Prev
    Next
    INDEX
    Explanations

    new things out now

    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
    ῞
    -1.59
     diſt
    -1.56
     perché
    -1.54
    rektur
    -1.54
     seulement
    -1.47
     proste
    -1.45
     sê
    -1.42
     extraordin
    -1.42
     persua
    -1.41
    eneuve
    -1.41
    POSITIVE LOGITS
     new
    1.76
     now
    1.57
     as
    1.54
     kişinin
    1.43
     учетом
    1.37
    人也
    1.35
     gewiß
    1.34
    Conclusiones
    1.30
    ajemen
    1.27
     cayó
    1.27
    Activations Density 0.031%

    No Known Activations