© 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. 90044
    Prev
    Next
    INDEX
    Explanations

    Supreme Court 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
    oum
    -0.69
    érée
    -0.69
    कड
    -0.68
     خلق
    -0.67
    miers
    -0.67
     creator
    -0.66
     Sosa
    -0.65
    Aub
    -0.64
    ContentAsync
    -0.64
     Lain
    -0.64
    POSITIVE LOGITS
    eline
    0.69
     electrification
    0.69
    ckeditor
    0.68
    herald
    0.61
     Southern
    0.60
    \{
    0.60
     Finley
    0.60
    促进
    0.60
    phen
    0.60
     régl
    0.60
    Activations Density 0.082%

    No Known Activations