© 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. 11892
    Prev
    Next
    INDEX
    Explanations

    pronouns like who whom

    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
     two
    -1.55
    ↵↵
    -1.55
    ждением
    -1.49
     sintió
    -1.46
    álně
    -1.46
    ↑↑↑
    -1.40
    🌸
    -1.39
     three
    -1.38
    们
    -1.37
     dessutom
    -1.35
    POSITIVE LOGITS
     who
    2.03
     we
    1.91
     mientras
    1.73
    Its
    1.66
      
    1.56
     lmao
    1.56
     cristianos
    1.55
        
    1.54
    </em>
    1.52
     quien
    1.49
    Activations Density 0.040%

    No Known Activations