© 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. 15822
    Prev
    Next
    INDEX
    Explanations

    being updated

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

    The neuron fires on tokens representing floating‐point or decimal numerical values (e.g. statistical/measured numbers with decimal points).

    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
    ⚔
    0.82
    па
    0.81
     ограни
    0.77
    יו
    0.76
    нето
    0.75
     Capitalism
    0.74
     Sizes
    0.73
    ಾದರೂ
    0.72
    OutSize
    0.72
     голе
    0.72
    POSITIVE LOGITS
     trừ
    0.83
    缘
    0.73
     kilometre
    0.72
     Hok
    0.70
     jel
    0.70
     weil
    0.69
     kaum
    0.69
    ों
    0.69
    bloom
    0.68
    lek
    0.68
    Activations Density 0.001%

    No Known Activations