© 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. 3864
    Prev
    Next
    INDEX
    Explanations

    EVM blockchain

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

    The neuron is strongly activated by numeric tokens representing non‐integer values (floating‐point 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
     Warnings
    0.79
     SYS
    0.78
     Tudo
    0.77
    handled
    0.73
     Five
    0.72
    广西
    0.72
     Він
    0.71
    😍
    0.71
    Five
    0.71
     lunga
    0.71
    POSITIVE LOGITS
     начи
    0.87
    ведена
    0.85
     автомати
    0.80
     высоко
    0.80
    ว์
    0.77
    ведите
    0.76
     invertir
    0.75
    ي
    0.75
    ﺔ
    0.75
    IDField
    0.73
    Activations Density 0.011%

    No Known Activations