© 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. 10545
    Prev
    Next
    INDEX
    Explanations

    Luxembourg and similar place names

    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
    閦
    -2.66
    ⼥
    -2.58
    𖣘
    -2.14
    autres
    -2.14
     Saltar
    -2.13
    ്ട
    -2.13
    AdvEx
    -2.09
    嗄
    -2.06
    メリカ
    -2.03
    mvh
    -2.03
    POSITIVE LOGITS
    ↵
    2.50
    ’
    2.41
    you
    2.41
    并在
    2.23
    而又
    2.22
    之际
    2.20
    骤
    2.11
     Luxembourg
    2.08
    但是在
    2.05
    ding
    1.98
    Activations Density 0.004%

    No Known Activations