© 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. 84833
    Prev
    Next
    INDEX
    Explanations

    file headers and copyright notices

    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
     Accessoires
    -0.84
     Nadal
    -0.83
    bof
    -0.81
     Vinci
    -0.81
    🖌
    -0.79
     BEGIN
    -0.77
     setuju
    -0.77
    fpm
    -0.76
     prix
    -0.75
     planen
    -0.75
    POSITIVE LOGITS
     adding
    0.84
     list
    0.81
     добавля
    0.78
    list
    0.76
    add
    0.76
     inviting
    0.75
     emplace
    0.74
    ancien
    0.73
    serializers
    0.73
    確保
    0.72
    Activations Density 0.001%

    No Known Activations