© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113064
    Prev
    Next
    INDEX
    Explanations

    network gateways and controllers

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

    technical terms and acronyms in telecommunications and networking contexts, particularly related to network infrastructure components like servers, gateways, nodes, and controllers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron consistently fires on uppercase technical acronyms and abbreviations naming network or telecom components (e.g. “Node B,” “UE,” “CPE,” “AT,” “gateway,” 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_10/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
     illustrationer
    -1.47
    cune
    -1.47
    ᝢ
    -1.46
    organisme
    -1.43
     hjemmeside
    -1.41
     ansatte
    -1.39
     lær
    -1.38
     bolig
    -1.38
     hvilket
    -1.37
     åp
    -1.36
    POSITIVE LOGITS
     Each
    1.39
            
    1.38
     giacca
    1.37
              
    1.32
    Each
    1.29
    
    1.25
    着他
    1.25
     if
    1.24
                    
    1.22
    A
    1.22
    Activations Density 0.103%

    No Known Activations