© 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. 33534
    Prev
    Next
    INDEX
    Explanations

    websocket connection

    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
    sendMail
    -0.90
     ransomware
    -0.89
     NCAA
    -0.79
     soleil
    -0.78
    VPN
    -0.77
     sunshine
    -0.76
     sun
    -0.75
     rocher
    -0.75
     phishing
    -0.74
    sendEmail
    -0.74
    POSITIVE LOGITS
     socket
    2.41
     WebSocket
    2.28
     websocket
    2.25
    socket
    2.16
     ws
    2.09
     Socket
    2.08
    WebSocket
    2.00
    websocket
    1.97
    Socket
    1.91
    ws
    1.89
    Activations Density 0.101%

    No Known Activations