© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105099
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     sypial
    -1.12
     cambios
    -1.10
     rè
    -0.97
     mulheres
    -0.96
    让你
    -0.95
     mesmos
    -0.94
     preços
    -0.94
     alterations
    -0.94
     accidentes
    -0.93
     áng
    -0.93
    POSITIVE LOGITS
     for
    1.23
     when
    1.23
     by
    1.21
     निम्नलिखित
    1.10
     Every
    1.05
    giau
    1.04
     Each
    1.02
     this
    1.02
     Additionally
    1.02
     From
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.