© 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. 86678
    Prev
    Next
    INDEX
    Explanations

    container; UI element; coding

    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
     during
    -1.72
     or
    -1.62
     by
    -1.52
     pelatih
    -1.46
     since
    -1.40
     Mereka
    -1.38
     to
    -1.38
     Pokud
    -1.33
     over
    -1.32
     in
    -1.30
    POSITIVE LOGITS
     autorizado
    1.58
     tornillos
    1.52
     versátil
    1.48
    龛
    1.48
     funcione
    1.41
    但却
    1.41
     duradero
    1.40
     geométrico
    1.40
     esperado
    1.39
     agujeros
    1.35
    Activations Density 0.013%

    No Known Activations