© 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. 13021
    Prev
    Next
    INDEX
    Explanations

    likely increase, batch, breathing, PE ratio

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

    This neuron fires on relatively rare or standout tokens—things like numbers, price or unit words, acronyms, and other uncommon or proper‐name–style tokens.

    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
     Некоторые
    1.05
     SIINFEKL
    1.03
     superoxide
    1.02
     PTFE
    0.99
     DUI
    0.96
     Бы
    0.95
     ゙
    0.94
     pancreatitis
    0.91
    izophren
    0.90
     обеспечивает
    0.89
    POSITIVE LOGITS
    de
    0.81
    et
    0.69
    ตรฐาน
    0.66
    าศ
    0.64
    da
    0.63
    こと
    0.61
    azza
    0.61
    ٬
    0.59
    ੋ
    0.59
    λα
    0.58
    Activations Density 0.000%

    No Known Activations