© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13462
    Prev
    Next
    INDEX
    Explanations

    vortices and defects

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

    The neuron consistently peaks on occurrences of the technical term “vortex” (and its inflected forms) in physics contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -1.71
     regardé
    -1.68
    especially
    -1.58
    world
    -1.57
    year
    -1.55
    se
    -1.53
    school
    -1.53
     Gennaio
    -1.52
     multicolore
    -1.52
    while
    -1.52
    POSITIVE LOGITS
    vga
    1.56
    cloudf
    1.56
    FEB
    1.55
    tvguide
    1.50
    皛
    1.41
    spb
    1.41
    狡
    1.40
    ambut
    1.38
    bermuda
    1.36
    زای
    1.36
    Activations Density 0.086%

    No Known Activations