© 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. 7908
    Prev
    Next
    INDEX
    Explanations

    REPORT Readers, names and titles

    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
     çünkü
    -1.52
     bardak
    -1.48
     \
    -1.48
     them
    -1.41
    他們
    -1.40
     etek
    -1.37
    यह
    -1.34
    嗬
    -1.34
     lanzó
    -1.33
    朝の
    -1.33
    POSITIVE LOGITS
            
    1.75
         
    1.66
           
    1.63
     still
    1.59
     Instead
    1.57
     נוסף
    1.52
     after
    1.52
       
    1.50
                
    1.49
     again
    1.46
    Activations Density 0.000%

    No Known Activations