© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8447
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron detects is references to heavy industrial machinery—particularly mining and construction crushers and related processing equipment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical or industrial content related to mining, manufacturing, machinery, and construction materials.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to mining and minerals, especially heavy equipment and processes for extracting, crushing, and processing ore and related industrial materials.

    oai_token-act-pair · gpt-5Triggered 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
     राधा
    0.62
     Burbank
    0.60
     தஞ்ச
    0.60
     Vaughn
    0.59
    ඪ
    0.58
    yczne
    0.57
    🍮
    0.57
     ストレ
    0.56
     বরিশাল
    0.55
    zur
    0.55
    POSITIVE LOGITS
     mining
    2.91
     Mining
    2.70
     miners
    2.69
    Mining
    2.64
     mined
    2.52
     mines
    2.50
     miner
    2.47
    mining
    2.44
    礦
    2.41
    矿
    2.39
    Activations Density 0.586%

    No Known Activations