© 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. 83444
    Prev
    Next
    INDEX
    Explanations

    network ports

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

    The neuron detects explicit references to network ports and related protocol fields (e.g. “port,” “tcp,” “dpt:,” source/destination) in technical or configuration contexts.

    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
    Superficie
    -0.71
    teils
    -0.71
    かれています
    -0.69
    Khan
    -0.68
     Khan
    -0.67
    ਖ
    -0.67
    cokinetic
    -0.67
     schrieb
    -0.66
    هب
    -0.66
    cliente
    -0.65
    POSITIVE LOGITS
     port
    4.06
     ports
    3.25
    port
    3.09
    Port
    3.08
     Port
    3.02
    端口
    2.83
    PORT
    2.64
     Ports
    2.48
     PORT
    2.48
     порт
    2.25
    Activations Density 0.122%

    No Known Activations