© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103445
    Prev
    Next
    INDEX
    Explanations

    legal orders

    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
    delicious
    -0.77
     panther
    -0.75
     quantità
    -0.74
     disfrut
    -0.73
     choisir
    -0.73
    transitions
    -0.73
    OOTD
    -0.71
     Cantidad
    -0.71
     Serpent
    -0.71
     viper
    -0.70
    POSITIVE LOGITS
     order
    2.86
     orders
    2.84
     Orders
    2.42
     Order
    2.25
    orders
    2.20
    order
    2.14
    Order
    2.08
    Orders
    2.08
    getOrder
    1.88
     ORDER
    1.81
    Activations Density 0.023%

    No Known Activations