© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41464
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and specific names

    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
     даже
    -1.34
     حتی
    -1.25
    他の
    -1.23
    Coucou
    -1.20
     speci
    -1.20
    rías
    -1.19
     nawet
    -1.18
    こんばんは
    -1.18
     навіть
    -1.18
     classique
    -1.17
    POSITIVE LOGITS
     not
    1.30
     then
    1.27
    .
    1.24
     entweder
    1.14
     chcete
    1.09
     that
    1.09
     along
    1.09
    ⅗
    1.08
     about
    1.06
    就
    1.05
    Activations Density 0.008%

    No Known Activations