© 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. 101194
    Prev
    Next
    INDEX
    Explanations

    time markers and subsequent events

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

    The neuron activates on adverbs and words that signal relative time (e.g. “昨日,” “上次,” “当日,” “recent,” “previous,” “this”).

    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
     -
    -2.58
     to
    -2.41
     of
    -2.31
     เพราะ
    -2.19
    ."
    -2.14
     '
    -2.13
    ,"
    -2.02
    可能会
    -2.02
     tinham
    -1.99
     were
    -1.98
    POSITIVE LOGITS
    䛗
    2.34
     soir
    2.33
    ઁ
    2.30
    ി
    2.22
    倂
    2.19
    оргаш
    2.17
    浤
    2.16
    emore
    2.16
    垵
    2.14
    al
    2.11
    Activations Density 0.000%

    No Known Activations