© 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. 74134
    Prev
    Next
    INDEX
    Explanations

    during events or periods

    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
    棪
    -1.47
    ższych
    -1.41
     increase
    -1.38
    荐
    -1.37
    刧
    -1.36
     Nanoparticles
    -1.35
     personnalisées
    -1.35
     provide
    -1.34
     enable
    -1.32
    翌
    -1.32
    POSITIVE LOGITS
     这
    1.73
     The
    1.70
     times
    1.48
     ""
    1.48
    {
    1.45
     ''
    1.41
    ぞれ
    1.38
     nicht
    1.36
    不能
    1.35
     ikke
    1.33
    Activations Density 0.055%

    No Known Activations