© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14015
    Prev
    Next
    INDEX
    Explanations

    days of the week and yesterday

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

    The main thing this neuron does is detect numeric tokens—especially figures denoting quantities, volumes, prices, shares, percentages, etc.

    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
    每年
    -1.63
     or
    -1.63
     to
    -1.26
     then
    -1.21
     can
    -1.20
     costs
    -1.13
    Ή
    -1.13
     project
    -1.11
     work
    -1.09
     for
    -1.09
    POSITIVE LOGITS
     yesterday
    1.98
    余談
    1.48
     Tuesday
    1.47
     gestern
    1.42
     Thursday
    1.41
     Friday
    1.41
    yesterday
    1.40
    俨
    1.39
     Saturday
    1.38
     Monday
    1.35
    Activations Density 0.005%

    No Known Activations