© 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. 34-GEMMASCOPE-RES-131K
    7. 108322
    Prev
    Next
    INDEX
    Explanations

    numbers followed by days

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

    The neuron spots numeric tokens and measurement quantities (standalone numbers, counts, and unit‐related digits) in 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_34/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
     month
    -2.47
    month
    -2.19
     months
    -2.16
    Month
    -1.94
     Month
    -1.89
     monthly
    -1.71
    MONTH
    -1.66
     meses
    -1.63
    months
    -1.55
     Months
    -1.55
    POSITIVE LOGITS
     days
    3.31
    Days
    2.52
     Days
    2.42
     DAYS
    2.28
    三天
    2.23
    days
    2.23
    DAYS
    2.05
    两天
    2.05
     días
    1.93
     giorni
    1.84
    Activations Density 0.128%

    No Known Activations