© 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. 32746
    Prev
    Next
    INDEX
    Explanations

    product properties and actions

    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
    banking
    -0.86
    airline
    -0.86
     oseb
    -0.85
    🤢
    -0.83
    MigrationBuilder
    -0.82
    todoList
    -0.82
    drawRect
    -0.80
    calend
    -0.79
     deviceId
    -0.78
    AccessFile
    -0.77
    POSITIVE LOGITS
     product
    2.72
     price
    2.44
     SKU
    1.95
     inventory
    1.89
     prices
    1.83
     sales
    1.81
    product
    1.77
     selling
    1.77
     products
    1.74
     purchase
    1.71
    Activations Density 0.117%

    No Known Activations