© 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. 98482
    Prev
    Next
    INDEX
    Explanations

    net, serve, line

    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
    戾
    -1.05
     Feedback
    -0.89
    Loyalty
    -0.77
    lük
    -0.75
    Feedback
    -0.73
     Loyalty
    -0.72
    Phosphorus
    -0.71
     Deletion
    -0.68
     suje
    -0.68
     Lucifer
    -0.68
    POSITIVE LOGITS
     net
    1.83
    Net
    1.50
    net
    1.48
     Net
    1.42
    NET
    1.30
     NET
    1.27
     nets
    1.21
     Netz
    1.20
     netted
    1.14
    ネット
    1.13
    Activations Density 0.014%

    No Known Activations