© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92863
    Prev
    Next
    INDEX
    Explanations

    Vietnamese names and places

    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
     Tiểu
    -1.59
     Thần
    -1.42
     Tử
    -1.29
     Địa
    -1.27
     Quận
    -1.13
     Quý
    -1.09
     Thiết
    -1.05
     Tư
    -1.05
     Chủ
    -1.05
     Máy
    -1.05
    POSITIVE LOGITS
     Vietnam
    2.13
     Vietnamese
    2.05
    Vietnam
    1.76
     Hanoi
    1.75
     Viet
    1.71
     Nguyen
    1.55
    Vietnamese
    1.48
     viet
    1.38
     Saigon
    1.36
    Viet
    1.20
    Activations Density 0.031%

    No Known Activations