© 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. 12151
    Prev
    Next
    INDEX
    Explanations

    during training, preparation, or leave

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

    The neuron fires on the word “During” when it introduces a time or date phrase.

    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
    w
    1.62
    il
    1.56
    am
    1.54
    m
    1.54
    ار
    1.51
    re
    1.39
    ad
    1.39
    v
    1.38
    l
    1.37
    en
    1.34
    POSITIVE LOGITS
    이나
    1.92
    د
    1.63
     وبعد
    1.59
    ى
    1.55
    ពេល
    1.52
    とその
    1.46
    ي
    1.46
     וכ
    1.42
     เช่น
    1.39
    BeerItem
    1.37
    Activations Density 0.076%

    No Known Activations