© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58851
    Prev
    Next
    INDEX
    Explanations

    day associated activities

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

    The neuron detects “day X” collocations—two-word phrases where “day” is followed by an activity or usage noun (e.g. day-trading, day-trips, day-spa).

    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
     мире
    -1.62
    utterstock
    -1.45
     муніципалі
    -1.44
    茑
    -1.37
     roky
    -1.37
    ౖ
    -1.36
    酝
    -1.36
    hmigung
    -1.35
     desolate
    -1.32
     désolés
    -1.31
    POSITIVE LOGITS
    '
    2.03
    c
    1.83
    Day
    1.66
    e
    1.57
     They
    1.55
    羮
    1.52
     daycare
    1.52
     of
    1.49
    q
    1.46
    :
    1.42
    Activations Density 0.019%

    No Known Activations