© 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. 128526
    Prev
    Next
    INDEX
    Explanations

    fine art & institutions

    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
    at
    -1.70
    素晴
    -1.66
    ‐
    -1.57
    ...
    -1.55
    т
    -1.54
    ).
    -1.52
                  
    -1.49
    -1.49
     企业
    -1.48
    up
    -1.48
    POSITIVE LOGITS
     джин
    1.74
     if
    1.73
     платье
    1.71
    祧
    1.70
     ensuring
    1.66
    𐐪
    1.66
     платья
    1.65
    蛧
    1.63
     пальто
    1.63
     Futebol
    1.63
    Activations Density 0.010%

    No Known Activations