© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129660
    Prev
    Next
    INDEX
    Explanations

    denoted by or abbreviated as

    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_22/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
          
    -1.30
         
    -1.28
    ↵↵
    -1.23
     один
    -1.20
     feier
    -1.16
      
    -1.13
     bestimmten
    -1.08
       
    -1.08
     wichtigen
    -1.06
     convert
    -1.04
    POSITIVE LOGITS
     miliki
    1.46
    
    1.34
     baumwolle
    1.33
     komer
    1.31
    Ꮔ
    1.30
    猡
    1.30
     rokok
    1.30
     kome
    1.29
     forem
    1.28
     técn
    1.27
    Activations Density 0.015%

    No Known Activations