© 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. 83074
    Prev
    Next
    INDEX
    Explanations

    chemical equations and formulas

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

    scientific notation and chemical formulas in technical documents.

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

    The neuron fires strongly on numeric tokens and number‐related expressions (digits, fractions, subscripts) typically found in technical or scientific contexts.

    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
    ErrorHandler
    -0.87
     Yar
    -0.81
    ameter
    -0.79
    tels
    -0.75
    ثیر
    -0.74
    zern
    -0.73
    terer
    -0.72
     gebeten
    -0.72
    вите
    -0.72
     Danilo
    -0.71
    POSITIVE LOGITS
     balanced
    2.28
    balanced
    1.94
     Balanced
    1.87
    Balanced
    1.85
     equation
    1.73
     unbalanced
    1.73
     balance
    1.70
     balancing
    1.66
     Balance
    1.60
     equations
    1.59
    Activations Density 0.013%

    No Known Activations