© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47689
    Prev
    Next
    INDEX
    Explanations

    in connection with

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

    This neuron detects phrases that signal linking or relationships between things—e.g. words like “connection,” “association,” “combination,” “partnership,” or “conjunction” when used with “with.”

    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
     in
    -1.27
    ,
    -0.86
    儀式
    -0.83
    另一方面
    -0.82
     respecto
    -0.81
     enable
    -0.77
     on
    -0.77
     In
    -0.75
     打
    -0.75
     engage
    -0.74
    POSITIVE LOGITS
    peration
    0.95
    □
    0.94
     eenen
    0.92
    efte
    0.91
    Também
    0.90
     тради
    0.90
    Outras
    0.88
    Então
    0.88
    ствие
    0.88
    skirts
    0.87
    Activations Density 0.038%

    No Known Activations