© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13360
    Prev
    Next
    INDEX
    Explanations

    what a book is

    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
    velse
    -1.49
     of
    -1.37
    ke
    -1.32
    wick
    -1.30
    similar
    -1.28
    in
    -1.27
    etc
    -1.27
     اولین
    -1.22
    лера
    -1.20
    aur
    -1.20
    POSITIVE LOGITS
     our
    1.45
    われ
    1.38
     caminando
    1.34
    embley
    1.31
     on
    1.29
    麾
    1.29
    我们将
    1.28
     unseres
    1.27
    深的
    1.27
     manchmal
    1.25
    Activations Density 0.053%

    No Known Activations