© 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. 76289
    Prev
    Next
    INDEX
    Explanations

    nutritional analyses and measurements

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

    scientific measurements and numeric values in academic papers, especially related to chemical composition and analysis.

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

    The main thing this neuron does is pick out numeric values and measurements (e.g. numbers, units, percentages) in scientific text.

    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
    INTAGE
    -0.91
    OBJETIVOS
    -0.80
     гай
    -0.79
     atributo
    -0.77
    كم
    -0.77
     منت
    -0.76
    奥运
    -0.75
     Brasilien
    -0.74
    glyph
    -0.74
    лу
    -0.74
    POSITIVE LOGITS
     total
    1.55
     protein
    1.51
     ash
    1.48
     crude
    1.37
     Ash
    1.30
     Protein
    1.20
     Crude
    1.13
    Protein
    1.12
    Crude
    1.08
    protein
    1.07
    Activations Density 0.051%

    No Known Activations