© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11888
    Prev
    Next
    INDEX
    Explanations

    over time

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

    The neuron is highly selective for the token “over” (especially when it’s used before a number or quantity, as in “over 10 years,” “over time,” 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_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
     decade
    0.86
     decades
    0.83
    decade
    0.80
     दशक
    0.75
    ー
    0.71
     décadas
    0.69
    ilot
    0.67
     nineties
    0.67
    á
    0.67
    bericht
    0.66
    POSITIVE LOGITS
     spans
    0.73
     lunes
    0.68
     расстояние
    0.64
     antara
    0.63
     に関
    0.63
     span
    0.62
     área
    0.62
     временем
    0.61
     curso
    0.61
    บริเวณ
    0.61
    Activations Density 0.086%

    No Known Activations