© 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. 106976
    Prev
    Next
    INDEX
    Explanations

    fluid flow behavior

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

    This neuron detects technical or scientific terminology typical of engineering and fluid‐dynamics contexts.

    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
    λίου
    -0.79
     Вя
    -0.71
     overlaps
    -0.71
    adone
    -0.70
    sexy
    -0.69
    tract
    -0.68
     prouver
    -0.67
     Proces
    -0.67
     Cheney
    -0.67
     compléter
    -0.66
    POSITIVE LOGITS
     flow
    1.65
     flows
    1.25
     Flow
    1.23
     airflow
    1.12
    flow
    1.09
     separation
    1.09
     stall
    1.06
    Flow
    1.06
     separated
    1.02
    Separated
    1.00
    Activations Density 0.035%

    No Known Activations