© 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. 69247
    Prev
    Next
    INDEX
    Explanations

    hereinafter referred

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

    The neuron selectively fires on rare or specialized single tokens—proper names, technical terms, jargon, and formal/legal words.

    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
    {
    -3.20
    氿
    -3.02
    s
    -2.83
    1
    -2.78
    ми
    -2.61
     Và
    -2.23
     выбирать
    -2.22
    的情况
    -2.20
     Hô
    -2.13
    -2.09
    POSITIVE LOGITS
    垰
    3.13
    偌
    3.08
     entrenched
    2.94
    蓠
    2.83
     sorta
    2.72
    呖
    2.59
    錞
    2.58
    ☫
    2.56
    那我
    2.55
    佧
    2.55
    Activations Density 0.016%

    No Known Activations