© 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. 84751
    Prev
    Next
    INDEX
    Explanations

    Apple, Steve Jobs, Pixar

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

    The neuron fires on capitalized personal names (proper names of individuals).

    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
    craper
    -0.92
    endregion
    -0.84
    وقتی
    -0.82
    Avengers
    -0.81
    安装
    -0.81
    イルド
    -0.80
    кость
    -0.80
    ആ
    -0.79
    ন
    -0.79
    蚁
    -0.79
    POSITIVE LOGITS
     Apple
    1.30
     Pixar
    1.16
    Apple
    1.10
     Silicon
    1.07
     ябло
    0.98
     Macintosh
    0.94
     PRODUCT
    0.91
     Stanford
    0.90
    Stanford
    0.88
     Jobs
    0.86
    Activations Density 0.024%

    No Known Activations