© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72533
    Prev
    Next
    INDEX
    Explanations

    saying that

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beberapa
    -1.46
     few
    -1.41
     poliuret
    -1.36
     Económica
    -1.35
     Ketika
    -1.30
    some
    -1.30
     Seperti
    -1.30
     
    -1.29
     niektórych
    -1.29
     الأخيرة
    -1.28
    POSITIVE LOGITS
     to
    2.31
     that
    1.72
         
    1.70
     That
    1.68
           
    1.64
     who
    1.59
                       
    1.57
     you
    1.52
              
    1.50
               
    1.45
    Activations Density 0.036%

    No Known Activations