© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6597
    Prev
    Next
    INDEX
    Explanations

    lightning and thunderstorm

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

    The neuron strongly activates on numeric measurements and associated meteorological units (e.g. wind speeds in mph, hail sizes, distances) in storm reports.

    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_31_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
    ☃
    0.61
     douceur
    0.58
    hbar
    0.56
     নিয়ন্ত্রণে
    0.56
    🍂
    0.56
    乾燥
    0.55
    晒
    0.55
    薛
    0.53
     কাশ্মীর
    0.52
     dryness
    0.52
    POSITIVE LOGITS
     thunderstorm
    1.57
     lightning
    1.53
     thunder
    1.42
     tornado
    1.42
    thunder
    1.39
     Thunder
    1.38
    Thunder
    1.38
     Lightning
    1.36
     thunderstorms
    1.34
     Tornado
    1.34
    Activations Density 0.103%

    No Known Activations