© 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. 69052
    Prev
    Next
    INDEX
    Explanations

    homozygous, sapiens, homocysteine, homosexual

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

    The neuron detects the word "homocysteine" and other variations with the prefix "homo-" (like homozygous, homozygote, homozygotes, etc.) in scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     is
    -2.50
    䜣
    -2.48
     persona
    -2.22
     entre
    -2.13
     '
    -2.08
     большая
    -2.08
     стоковые
    -2.08
     exitos
    -2.06
    説
    -2.05
     loo
    -1.95
    POSITIVE LOGITS
    Préparation
    2.47
    刳
    2.22
    櫪
    2.19
     イラストレーション
    2.16
    with
    2.14
    Matériel
    2.09
    Accueil
    2.06
    Плюсы
    2.06
    𖥧
    2.05
    ۠
    2.05
    Activations Density 0.022%

    No Known Activations