© 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. 123761
    Prev
    Next
    INDEX
    Explanations

    possessive determiners and French words

    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
    ों
    -2.83
    ࿊
    -2.52
    蚡
    -2.52
    你这个
    -2.23
    quelize
    -2.23
    螽
    -2.20
    s
    -2.19
    沨
    -2.17
    耵
    -2.08
     meisten
    -2.03
    POSITIVE LOGITS
     own
    3.33
     arată
    2.23
     Something
    2.23
     reveals
    2.20
    n
    2.19
     conferma
    2.09
    as
    2.02
    r
    2.02
    t
    1.97
     What
    1.96
    Activations Density 0.001%

    No Known Activations