© 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. 10-GEMMASCOPE-RES-131K
    7. 98750
    Prev
    Next
    INDEX
    Explanations

    units of time

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

    The neuron strongly activates on words that refer to current time frames—especially “this” plus a period (e.g. this month/this year/this week) or similar temporal markers like “today.”

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     länder
    -1.29
    きれ
    -1.27
    nością
    -1.16
     désormais
    -1.15
     Terkait
    -1.11
     consumidor
    -1.11
     acontec
    -1.10
     diário
    -1.10
     ก็
    -1.09
    口感
    -1.09
    POSITIVE LOGITS
     or
    1.67
     alebo
    1.48
     pomocą
    1.41
     mengucap
    1.30
     menetap
    1.28
     traditionnelle
    1.27
     membagikan
    1.22
     glaubte
    1.21
     memegang
    1.21
     any
    1.21
    Activations Density 0.026%

    No Known Activations