© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9297
    Prev
    Next
    INDEX
    Explanations

    start of sentence or title

    np_acts-logits-general · gemini-2.5-flash-lite

    width and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ago
    0.42
    磵
    0.40
    ar
    0.38
    ika
    0.38
    ola
    0.38
    ">'+
    0.38
    ɔ
    0.38
    ṭ
    0.38
    脖
    0.37
    ckiej
    0.37
    POSITIVE LOGITS
      
    1.95
       
    1.04
          
    0.90
        
    0.86
              
    0.83
            
    0.75
                      
    0.68
    0.66
                  
    0.66
         
    0.59
    Activations Density 0.134%

    No Known Activations