© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56937
    Prev
    Next
    INDEX
    Explanations

    code, proper names, width

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ⁉
    -0.97
     ALLA
    -0.96
     fasi
    -0.94
     pappa
    -0.93
     perfons
    -0.92
    .《
    -0.92
     dava
    -0.92
    politik
    -0.91
    "-"
    -0.90
     grammi
    -0.89
    POSITIVE LOGITS
     Is
    1.03
     Have
    0.96
                
    0.96
     Do
    0.96
                        
    0.93
     Has
    0.92
                 
    0.91
     ширина
    0.89
             
    0.87
     is
    0.87
    Activations Density 0.000%

    No Known Activations