© 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. 60554
    Prev
    Next
    INDEX
    Explanations

    XSLT or righteous

    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
    .
    -3.92
    ,
    -3.08
    {
    -2.78
    ↵↵
    -2.72
    us
    -2.72
    It
    -2.48
    ;
    -2.44
    q
    -2.42
    ,”
    -2.36
     During
    -2.33
    POSITIVE LOGITS
    
    2.86
     unſ
    2.86
     trám
    2.69
     ſever
    2.61
    ⮜
    2.56
    ⢅
    2.55
    ︕
    2.52
     anhänger
    2.50
     свою
    2.50
    ⑊
    2.47
    Activations Density 0.035%

    No Known Activations