© 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. 7389
    Prev
    Next
    INDEX
    Explanations

    flex;css display property

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

    The neuron detects structured e-commerce listing metadata fields—especially the “category” line (and related seller/location/shipping info).

    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
     ведь
    0.81
    arco
    0.77
    ீர்
    0.75
     assistir
    0.74
    ى
    0.74
    cador
    0.73
     zudem
    0.73
    arro
    0.73
    ª
    0.73
    ewell
    0.72
    POSITIVE LOGITS
     जाऊन
    0.85
     blocks
    0.71
     щоб
    0.70
     kinks
    0.69
     ints
    0.68
     views
    0.67
     있을
    0.66
     triangles
    0.66
     HAVE
    0.65
    mselves
    0.65
    Activations Density 0.007%

    No Known Activations