© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    periods of time

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

    The neuron detects expressions of time duration—especially phrases like “periods of time,” “extended periods of time,” or similar spans of 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
    utterstock
    -1.77
    笮
    -1.77
    
    -1.74
    設備
    -1.73
    replyreport
    -1.70
    ︳
    -1.65
    ൎ
    -1.62
    Через
    -1.62
     trovano
    -1.61
    玕
    -1.60
    POSITIVE LOGITS
     that
    1.62
    Y
    1.61
     која
    1.59
    ن
    1.59
    resultSet
    1.59
    *
    1.59
     Gebäude
    1.59
     '
    1.58
    n
    1.58
     which
    1.57
    Activations Density 0.008%

    No Known Activations