© 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. 104725
    Prev
    Next
    INDEX
    Explanations

    Emerson Weinstein Lyme disease

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

    personal and brand names, particularly recognizing specific surnames like Emerson, Weinstein, Lyme, and Kelli.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on capitalized named entities (proper nouns) such as person names, disease names, and other proper titles.

    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
     Our
    -2.81
     Are
    -2.73
    覺得
    -2.56
     Exploring
    -2.47
     assertions
    -2.41
     We
    -2.39
     الخارجية
    -2.25
    𐑂
    -2.23
    ль
    -2.20
     Only
    -2.17
    POSITIVE LOGITS
    襌
    2.78
    ⑊
    2.64
    ми
    2.45
    啬
    2.42
    瘩
    2.31
    噠
    2.28
    を始め
    2.27
     ヶ
    2.27
     cercare
    2.27
     bulundu
    2.25
    Activations Density 0.023%

    No Known Activations