© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119590
    Prev
    Next
    INDEX
    Explanations

    HTML tags and special characters

    np_acts-logits-general · gemini-2.5-flash-lite

    whitespace or spacing that appears before backslashes in LaTeX mathematical notation or code formatting.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
                    
    -2.14
    <blockquote>
    -2.03
    $
    -1.90
          
    -1.82
                            
    -1.76
                        
    -1.75
    可以
    -1.74
    ristiano
    -1.72
                       
    -1.70
     Now
    -1.70
    POSITIVE LOGITS
     aparência
    2.06
    s
    2.03
    呦
    1.84
    龃
    1.83
    e
    1.76
     verres
    1.74
     humeur
    1.73
     sólido
    1.70
    雰
    1.70
    牁
    1.63
    Activations Density 0.006%

    No Known Activations