© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2048
    Prev
    Next
    INDEX
    Explanations

    months

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

    The neuron is triggered by numeric tokens that are part of dates or timestamps (i.e. numbers following month names or in date‐style contexts).

    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_31_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
    なる
    0.59
    pct
    0.59
    ALT
    0.58
    溝
    0.58
    로운
    0.57
    tyle
    0.57
    由
    0.57
    褶
    0.56
    icted
    0.56
    🥞
    0.56
    POSITIVE LOGITS
    下旬
    1.02
     மாதம்
    0.96
     মাসের
    0.77
     tháng
    0.73
     মাসে
    0.71
     महीने
    0.68
     २०
    0.68
     ٢
    0.68
     २०१
    0.68
     Madness
    0.68
    Activations Density 0.224%

    No Known Activations