© 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. 11354
    Prev
    Next
    INDEX
    Explanations

    accuracy of information

    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
                
    -1.48
                    
    -1.34
                 
    -1.34
    :
    -1.33
              
    -1.32
                  
    -1.30
    -
    -1.30
    мой
    -1.28
    FOR
    -1.27
    द
    -1.21
    POSITIVE LOGITS
    Caracteristici
    1.47
    información
    1.45
    Să
    1.44
     verbinding
    1.42
     fotografías
    1.42
     that
    1.41
     поэтому
    1.41
     muertos
    1.40
    襯
    1.39
    ॑
    1.39
    Activations Density 0.054%

    No Known Activations