© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55262
    Prev
    Next
    INDEX
    Explanations

    fluid dynamics and turbulence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    戳
    0.48
     कॉले
    0.48
     cittam
    0.44
     tasmim
    0.44
    充电
    0.43
    ﹀
    0.43
    舆
    0.42
     प्रूव
    0.42
    䥑
    0.42
    㴓
    0.42
    POSITIVE LOGITS
     turbulence
    0.85
     turbulent
    0.77
     flow
    0.75
     Turbulence
    0.75
     laminar
    0.66
     CFD
    0.66
     Turbulent
    0.63
     Flow
    0.63
     hydrodynamic
    0.63
    流
    0.62
    Activations Density 0.063%

    No Known Activations