© 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. 12446
    Prev
    Next
    INDEX
    Explanations

    numbers and switch

    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
     الآخر
    -1.31
     possesso
    -1.30
    
    -1.28
    ICATION
    -1.26
     ricordo
    -1.23
     yielding
    -1.22
     SignIn
    -1.20
    %).
    -1.20
     relever
    -1.20
    Synonymes
    -1.20
    POSITIVE LOGITS
     But
    1.39
     as
    1.38
     najczęściej
    1.19
            
    1.16
      
    1.15
     généralement
    1.15
          
    1.13
    🌓
    1.13
              
    1.11
     and
    1.09
    Activations Density 0.030%

    No Known Activations