© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84717
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    
    -1.57
    ceis
    -1.56
    
    -1.50
    澌
    -1.47
     technischen
    -1.44
     защита
    -1.41
    ⢅
    -1.40
    ⚹
    -1.40
     emergencia
    -1.39
    拊
    -1.38
    POSITIVE LOGITS
    at
    2.22
     they
    2.00
    ،
    1.98
    ti
    1.48
     at
    1.47
     we
    1.47
     în
    1.47
    有没有
    1.41
     آن‌ها
    1.39
    Ᏺ
    1.38
    Activations Density 0.017%

    No Known Activations