© 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. 59739
    Prev
    Next
    INDEX
    Explanations

    fields and k

    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
     dnes
    -1.64
     ‘
    -1.62
    馓
    -1.50
     then
    -1.47
    ”)
    -1.42
     dollars
    -1.41
     ihan
    -1.41
     habile
    -1.41
    双方
    -1.38
    ?”
    -1.36
    POSITIVE LOGITS
    Гі
    1.44
     discou
    1.42
     appla
    1.41
    体现
    1.38
    ΕΛ
    1.37
     excels
    1.34
    侥
    1.32
    nąć
    1.28
    สำหรับ
    1.27
    bibliography
    1.26
    Activations Density 0.058%

    No Known Activations