© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10760
    Prev
    Next
    INDEX
    Explanations

    spiritual and astrological meanings

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

    The neuron strongly activates on explicit date, time, and astrology‐related tokens (months, numbers, New/New Moon, zodiac signs, planetary names) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Đấy
    0.75
    辄
    0.75
    📄
    0.73
    毎回
    0.72
     每个
    0.70
     ratus
    0.69
    РСР
    0.68
     sogen
    0.68
     Размер
    0.66
    ">${
    0.65
    POSITIVE LOGITS
     astral
    1.03
    あなたの
    0.97
     celestial
    0.96
     psychic
    0.96
     Astrology
    0.96
     cosmic
    0.91
     karm
    0.90
     astrological
    0.90
     astrolog
    0.89
     spiritual
    0.88
    Activations Density 0.101%

    No Known Activations