© 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. 10-GEMMASCOPE-RES-131K
    7. 60860
    Prev
    Next
    INDEX
    Explanations

    costumes, drag, and masquerade

    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
    (
    -2.11
    B
    -1.72
          
    -1.66
     that
    -1.61
        
    -1.58
       
    -1.56
             
    -1.48
    F
    -1.45
      
    -1.45
                    
    -1.43
    POSITIVE LOGITS
    FUENTES
    1.44
    垕
    1.44
    isations
    1.43
    IGNS
    1.41
     glabrous
    1.39
    CRIPTION
    1.39
    읖
    1.39
    immt
    1.38
    klärung
    1.38
    haviours
    1.34
    Activations Density 0.023%

    No Known Activations