© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30029
    Prev
    Next
    INDEX
    Explanations

    over the next

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

    This neuron detects temporal-duration expressions, especially phrases like “over the next/coming … years/months.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     depuis
    -1.21
     yesterday
    -1.18
     منذ
    -1.13
     آخرین
    -1.11
    去年
    -1.10
     letzte
    -1.09
     прошлом
    -1.09
    Yesterday
    -1.05
     earlier
    -1.04
     گذشته
    -0.98
    POSITIVE LOGITS
     next
    4.72
     coming
    3.08
     nächsten
    3.05
    next
    3.03
     próximos
    2.83
     komende
    2.69
     próximas
    2.67
     próxima
    2.59
    Next
    2.48
     próximo
    2.47
    Activations Density 0.055%

    No Known Activations