© 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. 98480
    Prev
    Next
    INDEX
    Explanations

    stable isotopes

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

    scientific terms related to stable isotopes in chemistry, geology, and physics research.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     formula
    -1.94
    Formula
    -1.77
    formula
    -1.70
     Formula
    -1.56
     formulas
    -1.55
     formulae
    -1.35
     fórmula
    -1.30
     Formulas
    -1.30
     FORMULA
    -1.25
     formule
    -1.07
    POSITIVE LOGITS
     isotopes
    2.14
     isotope
    2.00
     isotopic
    1.73
    isotope
    1.35
     Iso
    1.31
     mass
    1.10
    Iso
    1.08
     masses
    1.04
     ISO
    0.98
    iso
    0.96
    Activations Density 0.058%

    No Known Activations