© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47567
    Prev
    Next
    INDEX
    Explanations

    Sunday and dates

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

    The neuron strongly activates on the word “Sunday” (including its French form “dimanche”), i.e. occurrences of Sunday 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
     they
    -1.77
     &&
    -1.66
    nehm
    -1.55
    蚨
    -1.49
    皷
    -1.49
    手掌
    -1.47
     ก็
    -1.45
    猀
    -1.45
    "]/
    -1.41
     إجراء
    -1.41
    POSITIVE LOGITS
    This
    1.94
    ஂ
    1.88
     raiſ
    1.60
    The
    1.59
    Sunday
    1.57
    ｌ
    1.52
    We
    1.50
     herida
    1.49
    櫚
    1.49
    ]
    1.48
    Activations Density 0.035%

    No Known Activations