© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12590
    Prev
    Next
    INDEX
    Explanations

    family members and numbers

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

    The neuron fires most strongly on tokens naming family members (especially descendants) in obituary survivor lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alcoholism
    0.63
     governorship
    0.55
     govern
    0.52
     mutil
    0.52
    াভাবিক
    0.52
    🤣
    0.49
     ১৯৬
    0.48
    每年
    0.48
     বৎসর
    0.48
     সাহিত
    0.48
    POSITIVE LOGITS
     หนึ่ง
    0.75
     这个
    0.74
    ﻭ
    0.74
     ragazza
    0.73
    Debut
    0.73
    Wonderful
    0.72
    หนึ่ง
    0.71
     相关
    0.71
     Perempuan
    0.71
     Terbaru
    0.70
    Activations Density 0.015%

    No Known Activations