© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103763
    Prev
    Next
    INDEX
    Explanations

    suddenly followed by an event

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

    The neuron is a detector for the adverb “suddenly.”

    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
    {
    -2.59
    .”
    -2.50
    </strong>
    -2.48
     is
    -2.47
    ">
    -2.41
    ).
    -2.39
    淙
    -2.36
     At
    -2.33
    走吧
    -2.30
    We
    -2.27
    POSITIVE LOGITS
    鲧
    3.19
    笮
    2.94
    蘩
    2.86
    1
    2.64
    欉
    2.63
    喜歡的
    2.59
    t
    2.58
    還在
    2.58
    彀
    2.53
    ⎆
    2.53
    Activations Density 0.004%

    No Known Activations