© 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. 15141
    Prev
    Next
    INDEX
    Explanations

    html line breaks

    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
     هناك
    -2.11
     There
    -1.72
        
    -1.71
    sumoto
    -1.70
    ÁND
    -1.69
    犛
    -1.69
     promote
    -1.66
    ⇰
    -1.65
     warszaw
    -1.64
     began
    -1.62
    POSITIVE LOGITS
    those
    2.27
    −/−
    2.03
    跑到
    1.97
    凄い
    1.90
    ,;
    1.89
    ዣ
    1.88
    even
    1.88
    ,,,
    1.88
     proceeding
    1.88
    整个人
    1.87
    Activations Density 0.003%

    No Known Activations