© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98990
    Prev
    Next
    INDEX
    Explanations

    product images or photos

    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_34/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
     економі
    -0.85
    niosek
    -0.77
    átní
    -0.77
    ARCHITECT
    -0.75
    ùn
    -0.75
     Familienname
    -0.75
     头像
    -0.74
    дизайн
    -0.73
    cioni
    -0.73
     事件
    -0.72
    POSITIVE LOGITS
     product
    1.67
     images
    1.67
     main
    1.34
     image
    1.23
     zoom
    1.20
     Images
    1.15
    images
    1.14
     produit
    1.14
    product
    1.13
     photos
    1.12
    Activations Density 0.024%

    No Known Activations