© 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. 9287
    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
     "
    -1.19
     its
    -1.11
     an
    -0.93
     считается
    -0.91
     it
    -0.90
     three
    -0.89
    Though
    -0.87
    (
    -0.85
     five
    -0.83
    asının
    -0.83
    POSITIVE LOGITS
     télécharge
    1.06
    があって
    0.98
    躙
    0.96
    獏
    0.96
     rotación
    0.95
    橚
    0.94
     moſt
    0.94
    СТВО
    0.93
     étoiles
    0.93
     zustand
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.