© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15751
    Prev
    Next
    INDEX
    Explanations

    mathematical limits and drawable attributes

    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
    Negative Logits
     laajenta
    -1.61
     sisält
    -1.59
     jälkeen
    -1.59
    鶺
    -1.58
     eikä
    -1.51
     који
    -1.49
     encantó
    -1.49
     даже
    -1.49
     quedo
    -1.48
     suéter
    -1.48
    POSITIVE LOGITS
    aneity
    1.80
                 
    1.71
                    
    1.66
             
    1.62
               
    1.60
    摃
    1.57
    .
    1.55
              
    1.54
    you
    1.51
    alties
    1.51
    Activations Density 0.002%

    No Known Activations