© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6711
    Prev
    Next
    INDEX
    Explanations

    financial formulas (r, i, rt)

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

    The neuron fires on numeric tokens—especially floating‐point numbers—highlighting values like 419.5485, 728.1638, etc., in technical or data‐heavy 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_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
    g
    0.87
    y
    0.73
    daki
    0.67
    ي
    0.64
    gm
    0.64
    ppled
    0.63
    gang
    0.62
    dı
    0.62
    基
    0.62
    tu
    0.61
    POSITIVE LOGITS
     อาจารย์
    0.79
     dearly
    0.78
     дороже
    0.78
     معرف
    0.77
     televisión
    0.77
     emoción
    0.77
     молоко
    0.77
     вопросы
    0.76
     cartão
    0.76
     teorías
    0.76
    Activations Density 0.000%

    No Known Activations