© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42970
    Prev
    Next
    INDEX
    Explanations

    Segunda División, primera parte

    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
     ‘
    -3.34
    ’
    -3.23
      
    -3.03
    </strong>
    -2.78
                        
    -2.67
     
    -2.67
     {
    -2.63
    </h3>
    -2.48
             
    -2.47
    ↵
    -2.44
    POSITIVE LOGITS
     godk
    2.73
    禤
    2.72
     môžu
    2.59
     istimewa
    2.56
     森林
    2.48
     設備
    2.47
     kreatif
    2.47
     večer
    2.45
     majú
    2.44
     玩具
    2.42
    Activations Density 0.003%

    No Known Activations