© 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. 3528
    Prev
    Next
    INDEX
    Explanations

    hydrogen ions and neutralization

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

    chemical notation for ionic reactions, particularly proton (H+) exchange mechanisms.

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

    This neuron detects tokens representing charged chemical species or ion notation (e.g., H⁺, Na⁺/H⁺).

    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
     Investing
    -0.79
    왈
    -0.76
     Military
    -0.70
    Validity
    -0.70
    Military
    -0.69
     wysokiej
    -0.67
    日月
    -0.67
    軍
    -0.67
     lesbian
    -0.66
     galletas
    -0.66
    POSITIVE LOGITS
     hydrogen
    3.22
     Hydrogen
    2.78
    Hydrogen
    2.53
    hydrogen
    2.48
     protons
    2.31
     proton
    2.23
     Wasserstoff
    2.05
     Proton
    2.03
    氢
    1.80
     H
    1.64
    Activations Density 0.055%

    No Known Activations