© 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. 65002
    Prev
    Next
    INDEX
    Explanations

    group order

    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
     will
    -1.64
        
    -1.64
     is
    -1.62
           
    -1.60
     experience
    -1.59
              
    -1.59
            
    -1.54
                
    -1.54
             
    -1.52
     учетом
    -1.52
    POSITIVE LOGITS
     alerg
    1.70
     boute
    1.55
     avocat
    1.53
     Règlement
    1.52
     intrig
    1.51
     applau
    1.51
     thier
    1.50
     própri
    1.50
     rése
    1.48
     vives
    1.46
    Activations Density 0.172%

    No Known Activations