© 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. 98723
    Prev
    Next
    INDEX
    Explanations

    cross-lingual connective adverbs

    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
     it
    -2.56
     of
    -2.33
     you
    -1.89
                        
    -1.85
            
    -1.78
    {
    -1.75
                
    -1.73
                       
    -1.62
     They
    -1.62
     that
    -1.58
    POSITIVE LOGITS
    LayoutConstraint
    1.70
    ✽
    1.53
     emphasizes
    1.52
    鞦
    1.52
    исленность
    1.52
     ciś
    1.50
    álním
    1.49
     illustrates
    1.48
     started
    1.48
    deckung
    1.48
    Activations Density 0.006%

    No Known Activations