© 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. 22-GEMMASCOPE-RES-131K
    7. 128074
    Prev
    Next
    INDEX
    Explanations

    physics equations related to flux and pressure

    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_22/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
     to
    -1.30
     финансо
    -1.29
     execução
    -1.20
    nev
    -1.17
     tisíc
    -1.16
     vetores
    -1.14
     niebies
    -1.13
     Início
    -1.13
     sizin
    -1.12
    ziest
    -1.12
    POSITIVE LOGITS
     not
    1.77
     both
    1.16
     any
    1.15
     не
    1.13
    guitarra
    1.08
     cilindros
    1.08
    velocityY
    1.08
     angin
    1.07
     jambe
    1.06
    cinta
    1.05
    Activations Density 0.016%

    No Known Activations