© 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. 496
    Prev
    Next
    INDEX
    Explanations

    boxed numbers

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

    The neuron is triggered by HTML‐style character entities and other garbled or nonstandard Unicode encoding artifacts.

    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
    financ
    0.28
    お客
    0.27
     Новости
    0.26
    spolit
    0.26
    􀂃
    0.25
    speople
    0.25
    
    0.25
    
    0.25
     noticias
    0.25
     notícias
    0.25
    POSITIVE LOGITS
    0.28
     bilayer
    0.24
     creatinine
    0.23
     =
    0.23
    =\
    0.23
     equations
    0.22
     substituents
    0.22
     profinite
    0.22
     уравнения
    0.22
    4
    0.21
    Activations Density 0.033%

    No Known Activations