© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56942
    Prev
    Next
    INDEX
    Explanations

    chemical elements and ions

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

    chemical elements and their ions in scientific texts, particularly metals like Fe, Cu, Zn, Ni, and Mn with their oxidation states.

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

    The neuron fires on numeric chemical specifications—especially oxidation‐state labels in parentheses (e.g. “Fe(II)”, “U(VI)”) and element subscripts or ionic charges (e.g. “Mn2+”, “TiO2”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     ferric
    -1.05
     prosz
    -0.96
     now
    -0.93
     even
    -0.89
     those
    -0.88
     Bildern
    -0.86
     With
    -0.85
     Ministries
    -0.83
    giau
    -0.82
     escribiendo
    -0.82
    POSITIVE LOGITS
     atoms
    1.13
     content
    0.95
     atom
    0.88
     reager
    0.86
     isotopes
    0.86
     ดู
    0.83
     efficacité
    0.82
     '&
    0.81
     ions
    0.81
    conven
    0.81
    Activations Density 0.094%

    No Known Activations