© 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. 1064
    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
       
    -1.20
     based
    -1.16
        
    -1.10
     been
    -1.09
     con
    -1.03
    "
    -1.03
     can
    -0.99
     call
    -0.99
     pr
    -0.98
      
    -0.97
    POSITIVE LOGITS
     Anſ
    1.16
    焿
    1.15
    こんばん
    1.15
     menceritakan
    1.14
     tille
    1.13
     moter
    1.13
     nuits
    1.12
    <caption>
    1.11
    ؎
    1.11
    Zdra
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.