© 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. 38475
    Prev
    Next
    INDEX
    Explanations

    analytical data curves and spectra

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

    scientific measurement and analysis terms in technical papers, particularly related to chromatography, spectroscopy, and imaging techniques.

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

    The neuron detects numeric data tokens—numbers and measurement values appearing in the 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
     Shine
    -0.80
    mientos
    -0.74
     kiş
    -0.73
    Ǧ
    -0.73
    methods
    -0.73
     byen
    -0.73
    μου
    -0.73
     Minn
    -0.73
    番号
    -0.72
    logging
    -0.71
    POSITIVE LOGITS
     spectra
    2.36
     curves
    2.03
     profiles
    1.90
     spectrum
    1.67
     curve
    1.66
     profile
    1.66
     chromat
    1.64
    ograms
    1.53
    spectra
    1.51
     Curves
    1.46
    Activations Density 0.156%

    No Known Activations