© 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. 85100
    Prev
    Next
    INDEX
    Explanations

    included hardware and accessories

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     
    -1.42
    There
    -1.30
    year
    -1.26
    In
    -1.23
     there
    -1.21
    Perhaps
    -1.18
          
    -1.17
    because
    -1.16
     http
    -1.15
    かつ
    -1.15
    POSITIVE LOGITS
     that
    1.53
    컹
    1.35
    telah
    1.23
    
    1.23
     your
    1.18
    𓆉
    1.18
    primaryStage
    1.17
     preoc
    1.17
    <<<<<<<<<<<<
    1.16
     τὴν
    1.15
    Activations Density 0.054%

    No Known Activations