© 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. 21967
    Prev
    Next
    INDEX
    Explanations

    Maya and Mayan civilization

    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
     avec
    -2.88
    辚
    -2.75
    
    -2.70
    髕
    -2.69
    
    -2.67
    
    -2.66
    潆
    -2.64
    ,
    -2.64
    ఽ
    -2.64
    ,"
    -2.58
    POSITIVE LOGITS
    and
    2.78
    Y
    2.64
    {
    2.41
     they
    2.25
    🢒
    2.23
    но
    2.19
    e
    2.16
    入れた
    2.00
     autorisation
    1.99
     Its
    1.98
    Activations Density 0.002%

    No Known Activations