© 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. 29095
    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
    Making
    -0.90
    ことになる
    -0.89
     responsibility
    -0.88
    而后
    -0.87
    algunos
    -0.86
    那种
    -0.84
     Vand
    -0.84
    guidance
    -0.84
     dekoratif
    -0.83
    わけで
    -0.83
    POSITIVE LOGITS
    pylene
    1.03
    ARAN
    0.98
    िया
    0.94
    VideoView
    0.93
    landen
    0.91
    iexcl
    0.90
    ppé
    0.90
     Lernen
    0.89
     pygame
    0.89
     læ
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.