© 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. 65226
    Prev
    Next
    INDEX
    Explanations

    merge, publish, distribute

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

    The neuron fires on the key action words (e.g. “deal,” “merge,” “furnished,” “do,” “so”) that occur in open-source license grant clauses.

    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
     изпол
    -1.92
     like
    -1.85
    要望
    -1.76
     your
    -1.73
    ==""){
    -1.67
     propietarios
    -1.64
     bolsillos
    -1.64
     them
    -1.62
     inversores
    -1.61
     neumáticos
    -1.59
    POSITIVE LOGITS
     but
    2.34
    signable
    1.91
    tifiable
    1.91
    летка
    1.87
    ícias
    1.80
    ременно
    1.74
    rivial
    1.73
    ратор
    1.72
     могли
    1.71
    fillment
    1.70
    Activations Density 0.003%

    No Known Activations