© 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. 90736
    Prev
    Next
    INDEX
    Explanations

    saccharide or meister

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

    professional titles or roles (like maestro, meister, ester, seer) across various fields and languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires most strongly on longer, uncommon multi-syllabic content words—especially those of foreign or technical origin.

    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
    蓐
    -3.02
     arduous
    -2.78
    灃
    -2.70
    ότη
    -2.55
    ズニー
    -2.53
     trademark
    -2.52
     treacherous
    -2.52
    ▤
    -2.45
    𝄆
    -2.45
    里有
    -2.45
    POSITIVE LOGITS
    A
    4.47
    It
    3.63
    .
    3.47
    {
    2.92
    >
    2.91
    I
    2.89
    If
    2.86
    D
    2.73
    的
    2.64
    What
    2.61
    Activations Density 0.003%

    No Known Activations