© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8303
    Prev
    Next
    INDEX
    Explanations

    gold, silver, metallic items

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

    The neuron fires on mentions of specific metals, metal alloys, or metal finishes.

    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
    🍉
    0.71
    bble
    0.59
     fibras
    0.57
    timeouts
    0.57
     watermelon
    0.55
     polytope
    0.54
    Grunt
    0.54
     Davie
    0.54
    🥒
    0.54
     Kame
    0.53
    POSITIVE LOGITS
     gold
    2.11
     metals
    2.09
    金属
    1.94
     metal
    1.92
    gold
    1.92
    metals
    1.90
     Metals
    1.87
     golds
    1.84
     silver
    1.81
     золото
    1.81
    Activations Density 0.586%

    No Known Activations