© 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. 10-GEMMASCOPE-RES-131K
    7. 101799
    Prev
    Next
    INDEX
    Explanations

    Lopez, Daddy, Schneider, Diamond, Eva, Brockovich, Whitfield

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

    The neuron is a proper‐name detector, strongly activating on personal names (especially well‐known or celebrity surnames).

    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
    in
    -1.55
     zapewnia
    -1.48
     Ours
    -1.46
    {
    -1.46
    渺
    -1.45
     previamente
    -1.42
     Füßen
    -1.42
     This
    -1.41
     emergence
    -1.40
    ються
    -1.39
    POSITIVE LOGITS
    佧
    1.78
    这事
    1.77
     utiles
    1.61
     simples
    1.47
    目前的
    1.45
    стандарт
    1.45
    ྵ
    1.45
    这件事情
    1.41
    咵
    1.41
     quelle
    1.40
    Activations Density 0.009%

    No Known Activations