© 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. 61136
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    The neuron detects mentions of days of the week in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of specific weekdays (days of the week) and their immediate temporal context (e.g., morning, before/after).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    days of the week, particularly when referring to specific times or events.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     kdo
    -1.63
    沕
    -1.53
    𝐒
    -1.47
    toDouble
    -1.45
    Ű
    -1.45
    FlatStyle
    -1.39
    ácie
    -1.38
    telep
    -1.37
    ٨
    -1.37
     seguidores
    -1.36
    POSITIVE LOGITS
     of
    2.11
    ↵
    1.65
    of
    1.56
     которые
    1.41
    about
    1.41
     that
    1.38
     also
    1.37
     ambayo
    1.34
    的在
    1.31
    または
    1.30
    Activations Density 0.012%

    No Known Activations