© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43434
    Prev
    Next
    INDEX
    Explanations

    copper compounds and metals

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

    names of metals, particularly copper, zinc, and nickel.

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

    The main thing this neuron does is identify mentions of chemical element names (metals).

    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
    '
    -2.27
    澌
    -1.72
    f
    -1.71
    giaan
    -1.62
    半天
    -1.59
    だけど
    -1.55
    á
    -1.49
     they
    -1.45
    j
    -1.45
    卨
    -1.45
    POSITIVE LOGITS
    觏
    2.08
     It
    2.08
    copper
    2.00
    嵛
    1.80
     Copper
    1.80
    珦
    1.76
    떳
    1.68
    UCION
    1.66
    乆
    1.63
    Copper
    1.60
    Activations Density 0.019%

    No Known Activations