© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    working-class heroine

    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
     uphe
    -1.58
    纥
    -1.53
     SUCH
    -1.52
     bijvoorbeeld
    -1.47
    实际上
    -1.45
    比如说
    -1.38
     VARIOUS
    -1.38
     imponer
    -1.38
     özellikle
    -1.38
    に対し
    -1.37
    POSITIVE LOGITS
     mancha
    1.71
     vody
    1.67
    鱟
    1.64
     restaurantes
    1.59
    tricos
    1.54
     restos
    1.51
    𖤍
    1.49
    쫀
    1.49
    킁
    1.48
    ﾔ
    1.48
    Activations Density 0.017%

    No Known Activations