© 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. 4117
    Prev
    Next
    INDEX
    Explanations

    official orders and reports

    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
    óngase
    -0.79
     pardoned
    -0.78
     втор
    -0.76
    Introdu
    -0.73
     σαν
    -0.73
     Introdu
    -0.73
     distort
    -0.69
    怅
    -0.69
     тамо
    -0.69
    }}^{(
    -0.69
    POSITIVE LOGITS
     orders
    2.48
     order
    2.33
     cease
    2.02
    orders
    2.00
    order
    1.99
     ORDER
    1.90
    Order
    1.90
     Order
    1.86
     ordered
    1.80
     Orders
    1.77
    Activations Density 0.029%

    No Known Activations