© 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. 59742
    Prev
    Next
    INDEX
    Explanations

    metal-organic frameworks and complexes

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

    chemical formulas and molecular structures in scientific text.

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

    The neuron strongly activates on numeric tokens and element-symbol tokens within chemical formulas, i.e. the numbers and atom abbreviations that make up metal‐organic complex formulas.

    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
     during
    -0.77
     European
    -0.71
     конф
    -0.71
     and
    -0.70
     Rom
    -0.67
    vrier
    -0.66
    signol
    -0.65
    wenye
    -0.65
     chloride
    -0.65
    ภา
    -0.65
    POSITIVE LOGITS
     Tadeusz
    0.88
     koning
    0.87
     sortie
    0.87
     Kuli
    0.86
    жит
    0.84
     Dougherty
    0.84
    ){
    0.83
     cuit
    0.82
    ![](
    0.82
    вых
    0.82
    Activations Density 0.063%

    No Known Activations