© 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. 83261
    Prev
    Next
    INDEX
    Explanations

    connecting devices

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

    The neuron detects references to establishing connections (e.g. linking devices or networks).

    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
    ようになった
    -1.00
     Ngày
    -0.96
    結合
    -0.93
    sobre
    -0.92
    联系
    -0.91
     connection
    -0.91
     ayudarte
    -0.88
     oignon
    -0.85
    美味しかった
    -0.84
     départements
    -0.84
    POSITIVE LOGITS
     to
    2.17
     via
    1.91
     with
    1.46
    via
    1.16
     up
    1.11
     through
    1.08
     melalui
    1.02
    relenting
    1.00
     Via
    1.00
     darbo
    0.98
    Activations Density 0.073%

    No Known Activations