© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130901
    Prev
    Next
    INDEX
    Explanations

    traveling abroad

    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
    躄
    -2.77
    してます
    -2.47
    等の
    -2.39
    でご
    -2.38
    になりますが
    -2.31
     publicados
    -2.30
    蟜
    -2.27
    车上
    -2.17
    または
    -2.16
    鳔
    -2.14
    POSITIVE LOGITS
    s
    3.38
    t
    3.16
    料
    2.67
    ?
    2.63
    ↵↵
    2.50
    .
    2.45
     Abroad
    2.38
     abroad
    2.33
     carelessly
    2.30
    k
    2.28
    Activations Density 0.002%

    No Known Activations