© 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. 34-GEMMASCOPE-RES-131K
    7. 117409
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_34/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
    неопр
    -1.17
     pregn
    -0.85
     
    -0.79
    这不
    -0.79
    ()}}
    -0.78
     
    -0.76
     angebra
    -0.73
     ऐसे
    -0.73
    かもし
    -0.72
    exemplar
    -0.71
    POSITIVE LOGITS
      
    2.91
       
    1.44
        
    1.26
      
    1.04
          
    1.02
              
    0.84
    DBMS
    0.83
    gardens
    0.80
                  
    0.79
    jabat
    0.72
    Activations Density 0.296%

    No Known Activations