© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10883
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_40_width_16k_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
    屢
    0.40
    ¹
    0.36
     Graves
    0.35
    ή
    0.35
    ணா
    0.35
     уте
    0.35
    водитель
    0.34
    得る
    0.34
    бель
    0.34
     alimentare
    0.34
    POSITIVE LOGITS
       
    1.23
         
    0.93
           
    0.84
          
    0.84
        
    0.76
             
    0.65
               
    0.62
            
    0.61
                   
    0.55
                 
    0.54
    Activations Density 0.122%

    No Known Activations