© 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. 83356
    Prev
    Next
    INDEX
    Explanations

    firewall status and rules

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

    The neuron detects mentions of opening or configuring network ports and related firewall or iptables commands.

    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
    כה
    -0.80
    盖
    -0.77
     kwiaty
    -0.72
    ὃ
    -0.71
    蓋
    -0.71
    ռ
    -0.71
     faking
    -0.71
    テナ
    -0.69
    조
    -0.69
    Strike
    -0.69
    POSITIVE LOGITS
     firewall
    3.25
     Firewall
    2.41
     fire
    2.31
    firewall
    2.23
    Firewall
    2.05
     Fire
    1.79
    fire
    1.76
    防火
    1.70
    FIRE
    1.63
     FIRE
    1.63
    Activations Density 0.052%

    No Known Activations