© 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. 410
    Prev
    Next
    INDEX
    Explanations

    version numbers in code snippets

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

    The neuron detects mentions of pharmaceutical dosages, i.e. numeric strengths (e.g. “100 Mg”) often paired with drug names.

    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
     शिल्पा
    0.19
    <unused33>
    0.18
    ழந்த
    0.18
    ८
    0.17
    <unused49>
    0.17
    varchar
    0.17
    rante
    0.16
    崠
    0.16
    <unused56>
    0.16
    десь
    0.16
    POSITIVE LOGITS
    <unused439>
    0.20
     The
    0.18
    <unused326>
    0.18
     Zhen
    0.17
     Symptoms
    0.17
    <unused347>
    0.17
    <unused1926>
    0.17
    <unused720>
    0.17
     What
    0.16
     Özel
    0.16
    Activations Density 0.112%

    No Known Activations