© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61196
    Prev
    Next
    INDEX
    Explanations

    copper

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

    The neuron identifies chemical elements, particularly copper (Cu) and other metals in scientific contexts.

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

    The neuron primarily fires on occurrences of chemical element symbols (e.g. Cu, Zn, Al) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     they
    -1.95
    3
    -1.73
    .”
    -1.71
     is
    -1.60
    ”
    -1.55
    ’
    -1.48
    最重要的
    -1.45
     [
    -1.38
    .“
    -1.37
    2
    -1.35
    POSITIVE LOGITS
    نسي
    1.64
     använda
    1.63
     sentada
    1.61
    撷
    1.60
    geſ
    1.60
     disastrous
    1.57
    ienze
    1.56
    ꦒ
    1.56
    ﻪ
    1.56
    下载附件
    1.55
    Activations Density 0.052%

    No Known Activations