© 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. 10-GEMMASCOPE-RES-131K
    7. 9190
    Prev
    Next
    INDEX
    Explanations

    coupled with

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

    This neuron fires on the word “coupled” (especially as part of the phrase “coupled with”), marking instances of two things being linked or associated.

    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
    猡
    -2.56
    {
    -2.50
    </h1>
    -2.42
     unie
    -2.25
    ᕱ
    -2.17
     большая
    -2.16
     białym
    -2.09
    giaan
    -2.09
     cuadrados
    -2.05
    ⮜
    -2.05
    POSITIVE LOGITS
    </em>
    2.97
    .......
    2.73
    //
    2.67
    .....
    2.67
     It
    2.66
    ........
    2.64
    </td>
    2.59
    0
    2.53
    ......
    2.50
    This
    2.42
    Activations Density 0.010%

    No Known Activations