© 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. 2786
    Prev
    Next
    INDEX
    Explanations

    processes or states following "the"

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

    The neuron is triggered by numeric tokens containing decimal points (i.e. 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
     from
    0.55
     Quarry
    0.52
    一定的
    0.50
     a
    0.49
    全力
    0.46
    稿
    0.46
     Translated
    0.46
    ㅛ
    0.46
    ographed
    0.46
    ادف
    0.46
    POSITIVE LOGITS
     предотвра
    0.66
     proliferation
    0.61
     utilização
    0.57
     advancement
    0.57
     bezpiecze
    0.54
     betterment
    0.54
     pathologies
    0.53
     atrocities
    0.52
     hydrocarbon
    0.52
     utilización
    0.52
    Activations Density 0.006%

    No Known Activations