© 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. 10-GEMMASCOPE-RES-131K
    7. 14602
    Prev
    Next
    INDEX
    Explanations

    omelets

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

    The neuron fires on any token containing the substring “ome,” e.g. omelets, chamomile, liposomes, amebiasis, 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_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
    这
    -2.23
    をします
    -2.16
    这些
    -2.13
    さまで
    -1.97
    lında
    -1.92
    ﹍﹍
    -1.88
    你
    -1.82
    をしています
    -1.81
     vermelhas
    -1.81
     semelh
    -1.80
    POSITIVE LOGITS
     "
    2.27
     of
    2.00
    e
    1.96
     '
    1.79
    \\
    1.78
    ↵
    1.77
    1.65
     our
    1.63
    ',
    1.60
    ("
    1.59
    Activations Density 0.008%
    No Known Activations