© 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. 34-GEMMASCOPE-RES-131K
    7. 102519
    Prev
    Next
    INDEX
    Explanations

    chemical abundances and metallicity

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

    references to chemical composition or metallicity in scientific papers.

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

    The neuron is primarily firing on numeric expressions (measurements, quantities, and related symbols) in the scientific 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_34/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
    ANNUAL
    -0.81
    naux
    -0.73
     tritium
    -0.72
     hourglass
    -0.72
     Aarhus
    -0.71
    orescent
    -0.71
    struktion
    -0.68
    ECTS
    -0.68
     Annual
    -0.68
     Madame
    -0.68
    POSITIVE LOGITS
     abundance
    1.29
     metal
    1.23
     enrichment
    1.18
     abundances
    1.14
     Enrichment
    1.12
     enrich
    1.09
     heavy
    1.03
    enrich
    1.00
     Metal
    0.98
    abundance
    0.96
    Activations Density 0.023%

    No Known Activations