© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69233
    Prev
    Next
    INDEX
    Explanations

    mineral deposits

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

    mineral resources and mining-related terms including ore deposits, metals, exploration sites, and geological findings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects technical geology/mining terminology, especially references to ore and metal deposits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    受講
    -1.68
    授業
    -1.67
    Obsah
    -1.55
     kuhusu
    -1.55
     religieuses
    -1.45
     enfans
    -1.45
     espirituales
    -1.42
    研究生
    -1.39
    offered
    -1.38
    摂取
    -1.38
    POSITIVE LOGITS
     чехол
    1.31
    Lepid
    1.16
    ところ
    1.16
     Վերցված
    1.14
    ありますが
    1.13
     очистки
    1.13
    ֶּ
    1.10
     [''],
    1.09
     năm
    1.08
     tháng
    1.08
    Activations Density 0.003%

    No Known Activations