© 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. 34-GEMMASCOPE-RES-131K
    7. 99806
    Prev
    Next
    INDEX
    Explanations

    quantum algebra hierarchies

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

    The neuron detects specialized mathematical terminology—especially names of algebraic structures (e.g. “Lie algebras,” “integrable systems,” “Ad-invariant bilinear form,” “quantum current algebra,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     hostage
    -0.73
     Scul
    -0.71
     кало
    -0.69
    Naruto
    -0.68
    Péri
    -0.68
    estia
    -0.68
    光景
    -0.66
     tidligere
    -0.66
    晁
    -0.65
    Открыть
    -0.65
    POSITIVE LOGITS
    hbar
    0.88
     hierarchies
    0.86
     Schles
    0.85
    ugía
    0.82
     découvert
    0.76
     hierarchy
    0.76
     Mitter
    0.73
    Hierarchy
    0.73
     exceptionnelle
    0.70
     tenham
    0.69
    Activations Density 0.050%

    No Known Activations