© 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. 68761
    Prev
    Next
    INDEX
    Explanations

    time expressions

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

    The neuron is highly sensitive to the structural metadata tokens of a news article—things like section headings, dateline markers, timestamps (colons and numbers), and other layout punctuation.

    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
     old
    -1.25
     even
    -1.23
     their
    -1.21
     for
    -1.15
     because
    -1.12
     S
    -1.11
     A
    -1.11
     often
    -1.09
     NO
    -1.08
     Even
    -1.08
    POSITIVE LOGITS
     tonight
    1.80
     today
    1.70
     todays
    1.57
     Today
    1.44
     heute
    1.41
     сегодняш
    1.39
    today
    1.38
     tomorrow
    1.35
     recarg
    1.35
     dziś
    1.34
    Activations Density 0.010%

    No Known Activations