© 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. 12993
    Prev
    Next
    INDEX
    Explanations

    css units (px, rem, padding)

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

    The neuron is highly activated by numeric tokens, particularly 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
    结点
    0.78
    NA
    0.75
     있죠
    0.75
    旨在
    0.74
    })$;
    0.73
     Comando
    0.72
     crian
    0.72
    +}\
    0.72
     находятся
    0.72
    +)$
    0.71
    POSITIVE LOGITS
     roi
    0.79
    рін
    0.78
    czne
    0.75
    uche
    0.73
     technic
    0.73
     moi
    0.71
     checker
    0.71
    ړو
    0.71
    мо
    0.71
     physics
    0.68
    Activations Density 0.001%

    No Known Activations