© 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. 100486
    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
    %;
    -1.70
     Each
    -1.60
     ')
    -1.55
    <bos>
    -1.50
    ↵↵
    -1.48
     \
    -1.47
    +)$
    -1.46
    
    -1.43
     💗
    -1.42
    %">
    -1.40
    POSITIVE LOGITS
     signifikan
    1.55
     trattano
    1.52
    Jika
    1.50
     poteva
    1.45
    亮的
    1.41
     nella
    1.38
    皝
    1.38
    焯
    1.37
     وكان
    1.37
    みました
    1.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.