© 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. 10-GEMMASCOPE-RES-131K
    4. 39331
    Prev
    Next
    INDEX
    Explanations

    years and dates

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

    This neuron fires on the comma immediately following a full month–day–year date.

    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
     It
    -2.64
    {
    -2.36
    They
    -2.20
     Both
    -2.17
     Also
    -2.14
    Their
    -2.06
    If
    -2.03
    begin
    -1.88
     recommend
    -1.88
    There
    -1.82
    POSITIVE LOGITS
     "";
    2.47
     ''
    2.06
     конечно
    2.05
    蓐
    1.98
    戗
    1.96
    桄
    1.95
     ของ
    1.91
    栳
    1.86
    gencias
    1.85
    킨
    1.84
    Activations Density 0.102%

    No Known Activations