© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8757
    Prev
    Next
    INDEX
    Explanations

    jewelry and chains

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

    The neuron fires on mentions of jewelry-making components or hardware (e.g. caps, cones, beads, charms) used in assembling decorative jewelry.

    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
     ছাদে
    0.74
    篷
    0.64
     गन्ना
    0.59
    襖
    0.58
    contenedor
    0.57
     電動
    0.57
    棚
    0.56
    🏚
    0.56
     futebol
    0.55
    山西
    0.55
    POSITIVE LOGITS
     necklace
    2.48
     necklaces
    2.48
     jewelry
    2.42
     Jewelry
    2.30
     jewellery
    2.28
     Necklace
    2.23
     bracelet
    2.19
    jewelry
    2.14
    necklace
    2.13
     Jewellery
    2.11
    Activations Density 0.450%

    No Known Activations