© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10883
    Prev
    Next
    INDEX
    Explanations

    applicants more bet read

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

    variable assignment and definitions

    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
    koľ
    0.42
    ี้
    0.41
     XNUMX
    0.40
    τια
    0.39
    discard
    0.39
    成り立つ
    0.39
    ή
    0.39
    HEIM
    0.39
    成り
    0.38
    جرة
    0.38
    POSITIVE LOGITS
       
    1.74
         
    1.13
        
    1.02
           
    1.02
          
    0.85
               
    0.81
            
    0.78
             
    0.73
              
    0.72
                 
    0.65
    Activations Density 0.048%

    No Known Activations