© 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. 13927
    Prev
    Next
    INDEX
    Explanations

    advocating for, related to Global Phenomenon

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

    The neuron fires strongly on numeric tokens with large floating‐point values (i.e. multi‐digit decimal 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
    ,
    0.77
     slots
    0.71
     ,
    0.70
     중에서
    0.69
    놓
    0.69
     |
    0.68
     toys
    0.67
    Abstract
    0.66
    -
    0.64
    </blockquote>
    0.64
    POSITIVE LOGITS
    oclaw
    0.94
    يا
    0.93
     saludables
    0.90
    лы
    0.90
     reconocimiento
    0.88
     propias
    0.87
    ون
    0.87
    ánsito
    0.86
     opération
    0.86
    Ử
    0.85
    Activations Density 0.000%

    No Known Activations