© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7496
    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
    Until
    -1.18
     herrera
    -1.13
    här
    -1.12
    Оценка
    -1.11
    
    -1.10
     tää
    -1.10
     deri
    -1.10
    ☟
    -1.09
     vada
    -1.09
    ↓↓
    -1.09
    POSITIVE LOGITS
     og
    1.01
     g
    0.99
     sizzling
    0.95
     –
    0.94
     mas
    0.93
     gal
    0.91
     ayant
    0.91
    怖
    0.91
       
    0.91
    </em>
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.