© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5758
    Prev
    Next
    INDEX
    Explanations

    after or despite

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

    The neuron is looking for ordinal date suffixes (the “th” in dates like “7th,” “31st,” etc.).

    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
    ถ้า
    0.93
    ๕
    0.91
    ⁉
    0.89
    鿓
    0.88
     inflación
    0.88
    Panasonic
    0.87
    📨
    0.87
    盻
    0.87
    चुअल
    0.86
     penyakit
    0.86
    POSITIVE LOGITS
    k
    1.13
    et
    1.12
    y
    1.02
    al
    1.00
    o
    0.97
    e
    0.95
    m
    0.91
    en
    0.90
    am
    0.88
    as
    0.86
    Activations Density 0.003%

    No Known Activations