© 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. 71563
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron is strongly activated by numeric tokens—especially those representing dates, times, years, or other digit sequences in document metadata.

    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
    楽しんで
    -0.98
     woda
    -0.91
    knob
    -0.87
    常见的
    -0.86
    tember
    -0.85
     Մ
    -0.84
    应当
    -0.84
     anything
    -0.84
     einger
    -0.83
     terk
    -0.81
    POSITIVE LOGITS
     &
    1.08
     \&
    1.05
    Msg
    0.99
    angliski
    0.96
    Üdv
    0.95
     např
    0.94
     Univ
    0.93
     飯
    0.92
     yrs
    0.90
    Теперь
    0.90
    Activations Density 0.231%

    No Known Activations