© 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. 86589
    Prev
    Next
    INDEX
    Explanations

    percolation, diffusion, statistical mechanics

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

    The neuron strongly activates on technical, domain-specific scientific terms (e.g. biochemical, stochastic, percolation, monomers), i.e. specialized research vocabulary.

    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
    如果
    -1.77
    if
    -1.75
     Anſ
    -1.66
     then
    -1.64
     miele
    -1.59
     мечты
    -1.57
     ananas
    -1.54
    ֶּ
    -1.47
     balon
    -1.47
     siena
    -1.45
    POSITIVE LOGITS
     it
    1.68
    ₅
    1.62
     seguir
    1.51
     this
    1.50
    薗
    1.48
    setupUi
    1.46
     akce
    1.46
    槻
    1.45
    苫
    1.45
    俣
    1.41
    Activations Density 0.287%

    No Known Activations