© 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. 69035
    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
    onsumsi
    -0.96
    alisis
    -0.96
    䛗
    -0.94
     dites
    -0.93
    existent
    -0.93
    liśmy
    -0.90
    oprene
    -0.90
    浓郁
    -0.88
     realizar
    -0.88
     orlando
    -0.88
    POSITIVE LOGITS
     to
    1.00
    hdysval
    0.93
     neuesten
    0.93
     eventualmente
    0.90
     insidious
    0.89
     shameless
    0.88
    博物
    0.88
     repro
    0.88
    大丈夫です
    0.88
     Adding
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.