© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185701
    Prev
    Next
    INDEX
    Explanations

    places where people who

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

    Uneven

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    쐐
    0.53
     гипер
    0.51
     жиз
    0.47
    u
    0.46
     виде
    0.45
     postures
    0.45
    Guess
    0.45
    盽
    0.45
     ори
    0.45
     национа
    0.44
    POSITIVE LOGITS
                    
    0.51
                 
    0.48
              
    0.48
               
    0.47
     hans
    0.46
                  
    0.45
     televisi
    0.45
     beauté
    0.44
    becue
    0.43
     发布
    0.43
    Activations Density 0.000%

    No Known Activations