© 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. 93822
    Prev
    Next
    INDEX
    Explanations

    Navier-Stokes equations

    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
     cannon
    -0.80
     cannons
    -0.79
    nyi
    -0.72
    voort
    -0.70
     dug
    -0.70
     रही
    -0.69
     canon
    -0.69
     Micro
    -0.69
     Formel
    -0.69
     manually
    -0.69
    POSITIVE LOGITS
     buoyancy
    0.91
    gravity
    0.84
     isof
    0.81
     férias
    0.79
    Galer
    0.79
    بری
    0.77
     enclosure
    0.76
    ReusableCell
    0.76
     Rayleigh
    0.75
    Bou
    0.75
    Activations Density 0.016%

    No Known Activations