© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12798
    Prev
    Next
    INDEX
    Explanations

    k experts or secret keys

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

    The neuron responds to numeric tokens (e.g. page counts, years, prices, and other numbers).

    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
    아야
    0.82
    U
    0.75
     Vest
    0.73
    ﻄ
    0.72
    ្នក
    0.70
     sales
    0.69
     первой
    0.68
     výstav
    0.66
     exploration
    0.66
     XV
    0.65
    POSITIVE LOGITS
    زی
    0.89
    cuenta
    0.88
    ौरा
    0.86
    𝟎
    0.85
    ку
    0.84
    glial
    0.83
    矛
    0.82
    chromosome
    0.82
    mutex
    0.82
    PHPExcel
    0.82
    Activations Density 0.000%

    No Known Activations