© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23937
    Prev
    Next
    INDEX
    Explanations

    fluid flow in porous media

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    बाट
    -0.79
    anced
    -0.73
    monės
    -0.71
     спра
    -0.70
     chicago
    -0.70
    𝜖
    -0.70
     shad
    -0.69
    orian
    -0.69
     stij
    -0.69
     regresar
    -0.68
    POSITIVE LOGITS
     pore
    1.34
     permeability
    1.25
     Darcy
    1.20
     media
    1.16
     tort
    1.16
     rock
    1.11
     pores
    1.04
     porous
    1.04
     imbib
    0.98
    meability
    0.94
    Activations Density 0.045%

    No Known Activations