© 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. 34-GEMMASCOPE-RES-131K
    7. 63066
    Prev
    Next
    INDEX
    Explanations

    Phnom Penh, Cambodia

    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
     Thần
    -1.00
     Quý
    -0.84
    StringBuffer
    -0.83
     Ấ
    -0.83
    Cô
    -0.81
     Tử
    -0.80
     Puerto
    -0.77
    ឥ
    -0.75
    Thomas
    -0.75
    cripción
    -0.74
    POSITIVE LOGITS
     Cambodia
    2.28
     Cambodian
    2.22
     Khmer
    2.11
    Cambodia
    1.96
     Phnom
    1.88
     Cambo
    1.72
    Cambo
    1.66
    柬
    1.34
     Mekong
    1.18
    Sok
    1.02
    Activations Density 0.012%

    No Known Activations