© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92759
    Prev
    Next
    INDEX
    Explanations

    MQTT broker and QoS

    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
    magitan
    -0.75
    okra
    -0.75
     PTE
    -0.70
    Ema
    -0.68
     rę
    -0.67
    ทาน
    -0.67
     KBS
    -0.66
    Rudy
    -0.66
     Prefer
    -0.66
    Stre
    -0.65
    POSITIVE LOGITS
     broker
    1.42
    broker
    1.28
     QoS
    1.18
     MQTT
    1.16
     Broker
    1.13
    qos
    1.13
     brokers
    1.11
    Broker
    1.09
     topic
    1.04
    brokers
    1.02
    Activations Density 0.008%

    No Known Activations