© 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. 14944
    Prev
    Next
    INDEX
    Explanations

    website or social media page

    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
    </b>
    -1.38
    ");
    -1.29
    ());
    -1.24
     not
    -1.24
    太后
    -1.23
     blevet
    -1.22
     شیرین
    -1.20
    清明
    -1.19
     sólo
    -1.17
     When
    -1.16
    POSITIVE LOGITS
     website
    1.98
     webpage
    1.56
     websites
    1.49
     there
    1.49
     page
    1.48
    Mostrar
    1.48
     ресурсы
    1.44
     camiones
    1.40
    却又
    1.39
     soportes
    1.38
    Activations Density 0.106%

    No Known Activations