© 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. 69084
    Prev
    Next
    INDEX
    Explanations

    continues to

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

    The neuron fires on the recurring present-tense verb “continues,” especially in the construction “continues to.”

    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
    geſ
    -3.33
    <
    -2.91
     也
    -2.73
     sufri
    -2.55
    秾
    -2.52
     стал
    -2.45
    ⧠
    -2.44
     _______
    -2.41
     podemos
    -2.38
     ハ
    -2.33
    POSITIVE LOGITS
     火鍋
    2.94
    ;
    2.75
    緜
    2.70
    浥
    2.67
     That
    2.66
    賒
    2.66
    m
    2.61
     現貨
    2.58
    摃
    2.58
     zahlreiche
    2.55
    Activations Density 0.025%

    No Known Activations