© 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. 12576
    Prev
    Next
    INDEX
    Explanations

    kidney dialysis renal disease failure treatments

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

    The neuron flags highly domain-specific jargon, technical terms, acronyms, and specialized named entities across topics.

    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
     সত্যিকার
    0.60
    zej
    0.56
     ं
    0.55
     എഴു
    0.55
     bege
    0.55
    anjing
    0.55
     Paige
    0.54
     gatos
    0.54
     Bezirk
    0.54
     cộng
    0.54
    POSITIVE LOGITS
     निवेश
    0.63
    Mutual
    0.62
     mutual
    0.61
     Mutual
    0.61
     Ravi
    0.57
    債
    0.57
     investment
    0.56
     Debt
    0.55
     Investment
    0.53
     Chinese
    0.52
    Activations Density 0.038%

    No Known Activations