© 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. 14431
    Prev
    Next
    INDEX
    Explanations

    serve you

    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
     to
    -2.61
    什么
    -1.41
     kemudian
    -1.31
     iniz
    -1.30
     ameryka
    -1.30
     если
    -1.30
     notre
    -1.27
    玊
    -1.26
     zatem
    -1.25
     samme
    -1.23
    POSITIVE LOGITS
     with
    1.52
     vitre
    1.31
     Хотя
    1.29
    
    1.28
     Asturias
    1.27
     alimentazione
    1.27
    مية
    1.25
     entrée
    1.24
     crème
    1.24
    歴代
    1.23
    Activations Density 0.039%

    No Known Activations