© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7095
    Prev
    Next
    INDEX
    Explanations

    plugs and ports

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

    This neuron activates on mentions of hardware interface ports or connectors (e.g. DisplayPort, DVI-D, USB).

    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
     altında
    -0.79
    máquina
    -0.76
     prepare
    -0.76
    ulieren
    -0.76
     desea
    -0.76
    toplasm
    -0.75
    病気
    -0.74
     Wortes
    -0.73
     wires
    -0.71
    BRUARY
    -0.71
    POSITIVE LOGITS
     plug
    1.41
     plugging
    1.39
     plugged
    1.36
    plug
    1.20
     plugin
    1.12
    插
    1.12
     plugs
    1.11
     plugins
    1.11
     Plug
    1.11
    Plu
    1.06
    Activations Density 0.025%

    No Known Activations