© 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. 76071
    Prev
    Next
    INDEX
    Explanations

    publishing and subscribing topics

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on terminology and API calls related to publish–subscribe messaging (e.g. “Subscription,” “PubSub,” “subscribe,” “publish”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    appe
    -0.77
    راح
    -0.76
    Cisco
    -0.76
    臍
    -0.76
    github
    -0.76
     SMTP
    -0.75
    ᱹ
    -0.75
     feltro
    -0.74
    ddi
    -0.74
    enity
    -0.74
    POSITIVE LOGITS
     topic
    1.91
     Topic
    1.58
    Topic
    1.57
     topics
    1.55
     subscription
    1.53
    topic
    1.52
     subscriptions
    1.40
    Topics
    1.29
     Topics
    1.25
     publication
    1.22
    Activations Density 0.023%

    No Known Activations