© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72578
    Prev
    Next
    INDEX
    Explanations

    WooCommerce, Magento, e-shop

    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
    х
    -1.42
    是怎么回事
    -1.27
     anse
    -1.23
     -¿
    -1.23
     geogra
    -1.22
     reputa
    -1.21
     fixa
    -1.21
     servi
    -1.20
     appContext
    -1.19
    </h4>
    -1.18
    POSITIVE LOGITS
     одном
    1.63
    ropractor
    1.38
     entièrement
    1.38
     incense
    1.27
     رائع
    1.25
     značky
    1.23
     order
    1.22
     két
    1.20
    K
    1.16
     armados
    1.14
    Activations Density 0.070%

    No Known Activations