© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13305
    Prev
    Next
    INDEX
    Explanations

    times and dates

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

    This neuron detects time-of-day markers, specifically the “AM” and “PM” tokens in timestamps.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     It
    -0.98
     roligt
    -0.91
     tragé
    -0.91
     COM
    -0.90
     einen
    -0.90
    ного
    -0.89
    ctober
    -0.89
     Some
    -0.88
     big
    -0.88
     веке
    -0.85
    POSITIVE LOGITS
     carbur
    1.05
     influen
    1.04
     propon
    1.03
     rapor
    1.03
     avem
    0.96
    歘
    0.94
     conflic
    0.94
    Samedi
    0.93
    commonly
    0.93
    Vendredi
    0.92
    Activations Density 0.035%

    No Known Activations