© 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. 84264
    Prev
    Next
    INDEX
    Explanations

    now, today, current time

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

    The neuron strongly activates on numeric expressions (years, centuries, counts) and related punctuation, i.e. tokens representing numbers or numerical references.

    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
    age
    -1.00
     sempre
    -0.98
    より
    -0.91
     adet
    -0.88
     тради
    -0.86
     немного
    -0.84
    erving
    -0.84
     deeper
    -0.84
     अधिक
    -0.84
    ↵↵↵↵
    -0.83
    POSITIVE LOGITS
    今では
    1.66
     now
    1.63
     unrecogn
    1.30
    現在
    1.27
     today
    1.26
     transformed
    1.25
     сейчас
    1.22
    今は
    1.20
     sekarang
    1.16
    Сейчас
    1.16
    Activations Density 0.053%

    No Known Activations