© 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. 40186
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     leurs
    -1.34
     sellado
    -1.27
    ;%%
    -1.27
     of
    -1.26
     elevar
    -1.24
    Diverse
    -1.23
     wiele
    -1.19
     etc
    -1.18
     bepaalde
    -1.18
    Introducción
    -1.17
    POSITIVE LOGITS
     this
    1.47
    也是
    1.46
     these
    1.38
     Longueur
    1.34
    个
    1.33
    +"/"+
    1.31
    +
    1.30
    this
    1.28
    一個
    1.27
    在这
    1.26
    Activations Density 0.039%

    No Known Activations