© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107041
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and ions

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

    The neuron detects chemical elements and molecular formulas, particularly hydrogen (H) and other scientific notation in chemistry contexts.

    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
    Inhoud
    -0.81
     präsentieren
    -0.80
     技
    -0.77
     aprendiz
    -0.75
     distanci
    -0.75
     fertility
    -0.75
     المرجع
    -0.74
    adis
    -0.73
    oyu
    -0.73
    チア
    -0.71
    POSITIVE LOGITS
    +
    0.85
     II
    0.79
    Vé
    0.77
    +{
    0.73
    *'
    0.73
     Obre
    0.73
    Giorgio
    0.71
    )&&(
    0.71
     encountering
    0.70
     Corse
    0.69
    Activations Density 0.036%

    No Known Activations