© 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. 22-GEMMASCOPE-RES-131K
    7. 66714
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    tranh
    -1.06
     chêne
    -1.04
    zeitung
    -1.01
     coloriage
    -1.01
     kampen
    -0.96
    čené
    -0.96
     virke
    -0.96
     mercredi
    -0.95
     aktiviteter
    -0.95
    kegiatan
    -0.95
    POSITIVE LOGITS
     содержа
    1.00
     memberId
    0.95
     reasonable
    0.94
    覗
    0.93
    त्र
    0.93
    有一定
    0.93
     mList
    0.92
     bookId
    0.91
    olina
    0.90
     categoryId
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.