© 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. 73823
    Prev
    Next
    INDEX
    Explanations

    London entities and locations

    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
    vantaged
    -2.63
    .”
    -2.53
    '
    -2.47
    ﮏ
    -2.44
     próximas
    -2.28
     Все
    -2.28
    くちゃ
    -2.28
     рекомендуется
    -2.20
    他的
    -2.09
    งิน
    -2.05
    POSITIVE LOGITS
    鸶
    2.84
    翾
    2.53
    .
    2.42
    姈
    2.41
    纠结
    2.34
    lawayo
    2.34
     Our
    2.28
    襤
    2.22
     esteemed
    2.19
    之际
    2.14
    Activations Density 0.014%

    No Known Activations