© 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. 31599
    Prev
    Next
    INDEX
    Explanations

    sitting and waiting

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

    The neuron fires strongly on words and phrases that describe someone sitting or being seated (e.g. “sat,” “sits,” “sitting,” plus references to chairs, couches, stools, bedside, 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
     standing
    -2.16
     sitting
    -2.13
    Standing
    -2.05
     Standing
    -1.99
     sit
    -1.92
     Sitting
    -1.89
    Sitting
    -1.84
    standing
    -1.82
     sits
    -1.82
    sitting
    -1.77
    POSITIVE LOGITS
    等待
    1.28
     waiting
    1.24
    await
    1.20
     awaiting
    1.14
     await
    1.09
     watching
    1.07
     with
    1.00
     ждать
    0.95
     menunggu
    0.94
    waiting
    0.92
    Activations Density 0.055%

    No Known Activations