© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47851
    Prev
    Next
    INDEX
    Explanations

    FIG

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

    The neuron activates on the formal introductory sections of patent documents (e.g. “Field of the Invention,” “Background of the Art,” 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_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
     этой
    -2.03
     этого
    -1.90
     этих
    -1.89
     nowy
    -1.82
     same
    -1.80
    mathrm
    -1.80
     worin
    -1.76
    ⩽
    -1.75
     takie
    -1.75
               
    -1.73
    POSITIVE LOGITS
     mesmer
    1.89
    Jody
    1.86
    Другие
    1.84
     graisse
    1.81
    Общие
    1.81
    Kedves
    1.77
    Краси
    1.74
    Frida
    1.73
     as
    1.73
    曁
    1.72
    Activations Density 0.034%

    No Known Activations