© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77742
    Prev
    Next
    INDEX
    Explanations

    radioactive isotopes in chemical formulas

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

    radioisotope labels in scientific papers, particularly those with Carbon, Hydrogen, or Iodine isotopes.

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

    This neuron reliably activates on numeric isotope labels (e.g. “¹⁴C,” “³H,” etc.) used to denote radiolabeled or isotopically labeled compounds.

    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
     escribiendo
    -0.82
    淡淡的
    -0.81
     nebst
    -0.80
    にゃ
    -0.79
    osho
    -0.77
    꿇
    -0.77
    undi
    -0.75
    ченных
    -0.74
    onavirus
    -0.74
    ccedil
    -0.73
    POSITIVE LOGITS
    labeled
    0.99
     version
    0.90
     labeled
    0.89
     labelled
    0.88
     SPDX
    0.85
    Labeled
    0.79
     Reviewed
    0.78
    או
    0.78
     fumée
    0.78
    vânt
    0.77
    Activations Density 0.142%

    No Known Activations