© 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. 78195
    Prev
    Next
    INDEX
    Explanations

    viscoelastic properties

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

    This neuron detects terms related to viscoelasticity and rheological properties in scientific contexts.

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

    The neuron primarily detects mentions of “viscoelastic” (and its constituent parts “visco” and “elastic”).

    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
     modestly
    -0.71
     Algunas
    -0.71
     contes
    -0.70
     Será
    -0.67
    Divers
    -0.67
     Shifts
    -0.66
    Szia
    -0.65
    expliquer
    -0.64
    担心
    -0.64
    sunrise
    -0.64
    POSITIVE LOGITS
    metric
    0.79
     सि
    0.77
    metry
    0.77
    imetric
    0.77
     metric
    0.73
     így
    0.72
     gasket
    0.72
    imetry
    0.72
     rozwią
    0.71
    metrics
    0.70
    Activations Density 0.037%

    No Known Activations