© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49134
    Prev
    Next
    INDEX
    Explanations

    DNS resolution

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

    The neuron is triggered by numeric service identifiers—especially DNS port numbers and other protocol port or version numbers in technical scans and configurations.

    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
     assembler
    -1.20
     Assemble
    -1.11
     assemble
    -1.11
     assemb
    -1.09
     assembly
    -1.09
    Assembler
    -1.09
     Assembly
    -1.09
    assemb
    -1.07
     assemblies
    -1.02
     Assemb
    -0.97
    POSITIVE LOGITS
     DNS
    1.90
    DNS
    1.58
     dns
    1.42
    dns
    1.36
     resolution
    1.25
     resolver
    1.21
    Dns
    1.20
     Resolver
    1.18
    resolver
    1.17
    Resolution
    1.07
    Activations Density 0.027%

    No Known Activations