© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2371
    Prev
    Next
    INDEX
    Explanations

    code blocks and data structures

    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_22_width_262k_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
     sh
    0.62
    /
    0.61
     in
    0.60
    .
    0.60
    ,
    0.58
     quasi
    0.57
     prejudice
    0.56
     partially
    0.56
     at
    0.56
     BRA
    0.55
    POSITIVE LOGITS
            
    1.42
          
    1.36
         
    1.35
        
    1.31
                
    1.29
             
    1.29
           
    1.27
              
    1.21
               
    1.19
                 
    1.17
    Activations Density 0.467%

    No Known Activations