© 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. 44355
    Prev
    Next
    INDEX
    Explanations

    exactly, necessarily, much, especially

    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
    📰
    -1.35
     desafíos
    -1.35
    Ɍ
    -1.31
    
    -1.30
    rierte
    -1.27
     okna
    -1.25
     Perſ
    -1.24
    Один
    -1.23
     Pokud
    -1.23
    GGLE
    -1.22
    POSITIVE LOGITS
     which
    2.31
         
    1.76
     Which
    1.72
           
    1.69
       
    1.69
             
    1.48
    1.45
               
    1.44
                  
    1.44
                
    1.42
    Activations Density 0.017%

    No Known Activations