© 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. 90779
    Prev
    Next
    INDEX
    Explanations

    daniel Stenberg

    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
     урок
    -0.87
    Except
    -0.80
    自然是
    -0.79
     impresion
    -0.75
    ENTAL
    -0.74
     objekt
    -0.74
     converges
    -0.73
     принимает
    -0.73
    cite
    -0.73
     reveals
    -0.72
    POSITIVE LOGITS
     ¢
    0.94
    סת
    0.81
    aI
    0.80
    thyroidism
    0.78
    MATE
    0.77
    orgeous
    0.75
    wdata
    0.75
     hopefully
    0.74
     Ankunft
    0.74
     st
    0.73
    Activations Density 0.401%

    No Known Activations