© 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. 20726
    Prev
    Next
    INDEX
    Explanations

    names, places, and gmail

    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
     They
    -3.19
    牁
    -2.89
    ↵
    -2.70
     he
    -2.61
    ,”
    -2.59
    -2.48
    0
    -2.45
    â
    -2.34
     проблемы
    -2.22
     компании
    -2.17
    POSITIVE LOGITS
     hän
    2.97
    亹
    2.88
    ᠌
    2.41
    饜
    2.39
    嵎
    2.39
    鷙
    2.38
    
    2.33
    櫸
    2.33
    
    2.31
    结局
    2.28
    Activations Density 0.009%

    No Known Activations