© 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. 6701
    Prev
    Next
    INDEX
    Explanations

    symmetric simple, looking glass, Mc sorley

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

    The neuron strongly activates on technical mathematical terminology—particularly geometry and combinatorics definitions involving convex polytopes and integer coordinates.

    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
     Waterfall
    -0.82
    犧
    -0.81
     waterfalls
    -0.78
    存款
    -0.78
    circles
    -0.76
    administ
    -0.75
    committed
    -0.75
    тельств
    -0.74
     Zoltán
    -0.74
    ental
    -0.73
    POSITIVE LOGITS
     hyper
    1.46
    hyper
    1.24
     Hyper
    1.20
    Hyper
    1.12
     poly
    1.07
     facets
    1.04
     convex
    1.01
    zono
    1.00
     faces
    0.93
     affine
    0.92
    Activations Density 0.027%

    No Known Activations