© 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. 8363
    Prev
    Next
    INDEX
    Explanations

    born in or on

    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
     セール
    -1.38
    اگر
    -1.36
    感谢
    -1.34
    Ꭶ
    -1.34
     Yeti
    -1.33
     baha
    -1.33
    ఝ
    -1.33
    显示
    -1.32
    Funciones
    -1.32
     ofrecen
    -1.31
    POSITIVE LOGITS
     only
    1.90
     people
    1.75
     in
    1.73
     ONLY
    1.70
     on
    1.69
     Only
    1.68
     with
    1.62
     There
    1.59
     first
    1.57
     through
    1.54
    Activations Density 0.022%

    No Known Activations