© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2987
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric real-estate listing details—terms that quantify property features (e.g. bedroom counts, area measurements, “/” separators).

    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_31_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
    幢
    0.61
    oxin
    0.55
    ถนน
    0.55
    googleapis
    0.53
     ถนน
    0.53
    zahlen
    0.52
    akkh
    0.51
    =((
    0.51
    上市
    0.51
    aniy
    0.51
    POSITIVE LOGITS
     converted
    0.74
     storage
    0.66
     dressing
    0.64
     closet
    0.64
     cupboard
    0.64
     additional
    0.63
     niches
    0.63
     Dressing
    0.63
     niche
    0.63
     another
    0.63
    Activations Density 0.388%

    No Known Activations