© 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. 45211
    Prev
    Next
    INDEX
    Explanations

    TCP packet size and bandwidth

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

    The neuron is selectively activating on technical networking terms and jargon (e.g. TCP, congestion, packet, bandwidth, etc.).

    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
     برابوك
    -0.83
    <0x9A>
    -0.77
     Emotions
    -0.73
    ยก
    -0.73
     trừ
    -0.73
    kinci
    -0.73
    coration
    -0.71
     dagger
    -0.71
     Emotion
    -0.71
    转化
    -0.71
    POSITIVE LOGITS
     congestion
    1.06
     Reno
    0.94
     probes
    0.92
    拥
    0.90
     bandwidth
    0.88
     probing
    0.84
     TCP
    0.84
     Cong
    0.84
     Bandwidth
    0.81
    ⃝
    0.77
    Activations Density 0.018%

    No Known Activations