© 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. 19516
    Prev
    Next
    INDEX
    Explanations

    ecclesiastical, Eccles, time

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

    The neuron is triggered by the word “time” (in any context or casing), as in titles like “A Time to Kill” or phrases like “beautiful … in its time.”

    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
    ΅
    -1.77
    齶
    -1.73
    埽
    -1.70
    鹇
    -1.62
    妗
    -1.59
    ༔
    -1.55
     the
    -1.55
    ೢ
    -1.55
     deliciously
    -1.54
    埛
    -1.54
    POSITIVE LOGITS
     for
    2.69
    ,
    1.89
     on
    1.61
    (
    1.56
    _
    1.49
    -
    1.46
     at
    1.44
    采用
    1.34
    For
    1.34
     Makes
    1.33
    Activations Density 0.006%

    No Known Activations