© 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. 87164
    Prev
    Next
    INDEX
    Explanations

    instructed to represent

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

    task, need, rent, panels

    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
     trái
    0.57
     कोश
    0.46
     œufs
    0.46
     недвижимости
    0.46
    轂
    0.46
    缇
    0.45
     Unternehmens
    0.45
    簹
    0.44
     လက်
    0.44
     Architektur
    0.43
    POSITIVE LOGITS
    6
    0.52
    5
    0.51
    0
    0.50
                  
    0.48
     alone
    0.48
                                   
    0.47
                            
    0.47
              
    0.47
                             
    0.46
    7
    0.46
    Activations Density 0.000%

    No Known Activations