© 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. 39021
    Prev
    Next
    INDEX
    Explanations

    effect, play, applicable

    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
    ↵
    -2.11
    了很多
    -1.88
    了一個
    -1.77
    了许多
    -1.73
    了不少
    -1.70
    -
    -1.67
    #
    -1.66
    了好
    -1.64
     übrigens
    -1.61
     Commonly
    -1.59
    POSITIVE LOGITS
    droj
    1.75
     geel
    1.60
     berge
    1.60
     it
    1.59
    hå
    1.59
    桕
    1.56
    ᕱ
    1.55
     ◄
    1.55
     آن‌ها
    1.53
     fondamental
    1.52
    Activations Density 0.201%

    No Known Activations