© 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. 21815
    Prev
    Next
    INDEX
    Explanations

    avant-garde, Lao, NaOH, alkali

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

    The neuron detects terms related to avant-garde art movements and chemical compounds like sodium hydroxide (NaOH).

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

    The neuron fires on occurrences of the substring “avant” (as in “avant-garde”).

    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
    蔸
    -3.14
    訁
    -2.81
     erwähnten
    -2.73
     ไม่
    -2.70
     eſſ
    -2.56
    喑
    -2.45
     möglichen
    -2.42
    一开始
    -2.41
    ⏑
    -2.33
    튿
    -2.33
    POSITIVE LOGITS
    {
    3.50
    The
    3.02
    It
    2.73
    o
    2.56
     Technically
    2.36
     mexicano
    2.23
    Interestingly
    2.17
    境内
    2.17
    There
    2.13
    鼙
    2.13
    Activations Density 0.003%

    No Known Activations