© 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. 130666
    Prev
    Next
    INDEX
    Explanations

    associate sales partners

    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
     so
    -1.57
     of
    -1.34
     foi
    -1.23
    zkiem
    -1.16
     we
    -1.16
    ريقيا
    -1.14
     again
    -1.13
     edición
    -1.12
     persua
    -1.11
     augusti
    -1.11
    POSITIVE LOGITS
     flexibilidad
    1.31
     ativos
    1.26
     destinés
    1.21
     respiración
    1.18
     ventilación
    1.17
     compresión
    1.16
    櫥
    1.16
     destinados
    1.13
     who
    1.10
     destinées
    1.10
    Activations Density 0.097%

    No Known Activations