© 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. 11215
    Prev
    Next
    INDEX
    Explanations

    writing lists and sections

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

    The neuron fires on numeric tokens that look like floating‐point numbers or decimal values.

    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
    ა
    0.79
    łeś
    0.75
    cón
    0.70
     Ná
    0.69
    権利
    0.69
    orre
    0.69
    decorators
    0.69
    sites
    0.68
    CharArray
    0.68
    ୟ
    0.68
    POSITIVE LOGITS
     роботи
    0.80
     byproduct
    0.76
     устра
    0.74
     cosmology
    0.73
     проек
    0.73
     чай
    0.71
     conferencing
    0.68
     orden
    0.68
     corpse
    0.67
     entscheiden
    0.67
    Activations Density 0.003%

    No Known Activations