© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2830
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     socalled
    1.60
     wellknown
    1.45
    -”
    1.10
    昀
    1.04
     “[
    0.99
    <unused1146>
    0.98
    (“
    0.96
    ƣ
    0.94
    甃
    0.90
     
    0.89
    POSITIVE LOGITS
      
    5.50
       
    4.55
        
    3.61
         
    3.25
          
    3.13
           
    2.79
            
    2.59
              
    2.57
             
    2.48
    <0xE3>
    2.35
    Activations Density 5.508%

    No Known Activations