© 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. 12322
    Prev
    Next
    INDEX
    Explanations

    `form`, `Raw`, `SMA`, `EMA`

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

    the neuron identifies tokens that are floating‐point numbers (numerical values containing a decimal point).

    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
    query
    0.74
     perjud
    0.68
     problema
    0.68
    ஹ
    0.66
     архіви
    0.65
    viewer
    0.65
     somente
    0.64
    いつも
    0.64
     verificare
    0.64
    วิธี
    0.63
    POSITIVE LOGITS
    daki
    0.83
    blusas
    0.79
     Помимо
    0.79
    靈
    0.79
     Matcha
    0.79
    lera
    0.78
    itamins
    0.78
     """"
    0.77
     Woche
    0.77
    Huh
    0.77
    Activations Density 0.000%

    No Known Activations