© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153314
    Prev
    Next
    INDEX
    Explanations

    fluid dynamics

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

    turbulence and fluid flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    舆
    0.51
    戳
    0.47
    癃
    0.47
    充电
    0.47
     پارٹی
    0.46
    停车
    0.46
    صرية
    0.46
    埚
    0.46
    辂
    0.46
    经纪
    0.45
    POSITIVE LOGITS
     turbulence
    1.01
     convective
    0.93
     convection
    0.91
     turbulent
    0.87
    turbulence
    0.83
     flow
    0.81
     hydrodynamic
    0.81
     Turbulence
    0.79
     laminar
    0.79
    flow
    0.74
    Activations Density 0.052%

    No Known Activations