© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118087
    Prev
    Next
    INDEX
    Explanations

    Mughlai cuisine and Indian emperors

    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_34/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
     Surya
    -0.82
     Glyco
    -0.81
    군
    -0.77
     соло
    -0.76
    дравствуйте
    -0.75
     מר
    -0.72
    Pantalla
    -0.69
     Aris
    -0.68
    Nj
    -0.67
    ח
    -0.67
    POSITIVE LOGITS
     emperor
    1.35
     Emperor
    1.30
     Mughal
    1.26
     emperors
    1.05
     Agra
    1.03
    Agra
    1.00
     Emper
    0.99
     India
    0.98
     Akbar
    0.98
     Delhi
    0.95
    Activations Density 0.016%

    No Known Activations