© 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. 10-GEMMASCOPE-RES-131K
    7. 14227
    Prev
    Next
    INDEX
    Explanations

    immigration and naturalization

    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
    发的
    -1.26
    pper
    -1.20
     tersebut
    -1.20
     domestique
    -1.18
    乐趣
    -1.18
    inty
    -1.17
    丄
    -1.17
    ża
    -1.17
     هایی
    -1.16
     vermute
    -1.16
    POSITIVE LOGITS
    ^{\
    1.29
     следу
    1.20
     immigration
    1.20
     особенно
    1.17
    zef
    1.16
     když
    1.14
     back
    1.13
    胄
    1.13
    させて頂きます
    1.13
    ثیر
    1.11
    Activations Density 0.055%

    No Known Activations