© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8647
    Prev
    Next
    INDEX
    Explanations

    viscosity, viscous, viscoelastic

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

    The neuron detects the word "viscosity" and related fluid property terms in scientific or technical contexts.

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

    The neuron fires on mentions of viscosity or related rheological (fluid‐flow) properties.

    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
    …’
    -2.52
    actéristi
    -2.38
     certamente
    -2.34
     Coupled
    -2.34
    ’,
    -2.34
    乄
    -2.31
     terceiros
    -2.22
     Especially
    -2.17
     positioned
    -2.17
    ㊁
    -2.14
    POSITIVE LOGITS
     она
    2.27
    b
    2.22
    i
    2.14
    مشخصات
    1.99
    <bos>
    1.99
     resolute
    1.91
    と
    1.90
     litros
    1.89
    uertos
    1.88
    い
    1.88
    Activations Density 0.004%

    No Known Activations