© 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. 22-GEMMASCOPE-RES-131K
    7. 66503
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with subscripts

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

    chemical formulas with numeric subscripts and mathematical notation in scientific papers.

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

    The neuron fires on numeric tokens—particularly the numbers and numeric subscripts that appear in chemical formulas or composition ratios.

    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
     after
    -1.16
     setelah
    -1.13
     when
    -1.06
     a
    -1.02
     help
    -1.02
     после
    -1.01
     visit
    -1.00
     祝福
    -1.00
     rekomendasi
    -0.98
     use
    -0.98
    POSITIVE LOGITS
    határoz
    1.06
    diğimiz
    1.04
    pushd
    1.03
     mathvariant
    1.02
    迈
    1.02
     掛け
    1.01
     mécan
    1.00
    %{
    1.00
    ילת
    0.99
     kész
    0.98
    Activations Density 0.020%

    No Known Activations