© 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. 10-GEMMASCOPE-RES-131K
    7. 10976
    Prev
    Next
    INDEX
    Explanations

    dates with commas

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

    The neuron activates on numeric tokens (dates, times, scores, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     crochê
    -1.48
     silang
    -1.30
     palio
    -1.27
     katanya
    -1.25
     klaus
    -1.24
     ujar
    -1.23
     简
    -1.23
     sapat
    -1.23
     siena
    -1.22
     anta
    -1.22
    POSITIVE LOGITS
    ."
    1.27
     estando
    1.27
     its
    1.25
    Jack
    1.23
     own
    1.20
     takich
    1.20
    oks
    1.18
    </i>
    1.18
     typu
    1.16
    のいい
    1.15
    Activations Density 0.153%

    No Known Activations