© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1339
    Prev
    Next
    INDEX
    Explanations

    european languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     socalled
    1.92
     wellknown
    1.83
     longterm
    1.19
     阅读全文
    1.13
    
    0.91
    <unused2172>
    0.87
    <unused1756>
    0.85
    <unused335>
    0.84
    癥
    0.83
    <unused2180>
    0.83
    POSITIVE LOGITS
      
    6.73
       
    5.65
        
    4.30
         
    4.11
          
    4.06
           
    3.67
              
    3.49
             
    3.38
            
    3.31
               
    3.23
    Activations Density 1.276%

    No Known Activations