© 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. 102686
    Prev
    Next
    INDEX
    Explanations

    numerical ratings and scores

    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
     werkzaam
    -1.15
     روسيا
    -1.14
    -
    -1.11
     отца
    -1.09
     солнце
    -1.09
     inklusive
    -1.09
    OrderItem
    -1.08
    擔心
    -1.08
     WIL
    -1.08
     lequel
    -1.08
    POSITIVE LOGITS
     because
    1.62
     they
    1.59
     more
    1.34
     during
    1.32
    商品説明
    1.29
     malang
    1.24
     prolonged
    1.24
    DESCRIPCIÓN
    1.23
    Questão
    1.22
    女優
    1.21
    Activations Density 0.042%

    No Known Activations