© 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. 764
    Prev
    Next
    INDEX
    Explanations

    remote desktop protocol RDP

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

    This neuron fires on technical terms related to remote‐desktop/terminal‐server components and protocols (e.g. Guacamole audio/socket encoder identifiers, “Terminal Server,” “RDP,” “remote desktop,” 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
     quiver
    -0.82
    ratore
    -0.81
    ⌐
    -0.79
    replaceAll
    -0.73
     HTTP
    -0.71
    viv
    -0.71
     Apo
    -0.71
    Messaging
    -0.70
    وسف
    -0.70
     Image
    -0.69
    POSITIVE LOGITS
     RDP
    1.03
     mst
    0.97
    rds
    0.88
    rdp
    0.85
     RDS
    0.80
    RDS
    0.77
     compreensão
    0.76
     NLA
    0.76
     RD
    0.75
    RAIL
    0.72
    Activations Density 0.016%

    No Known Activations