© 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. 62407
    Prev
    Next
    INDEX
    Explanations

    dietary fiber components

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

    content related to dietary fiber and digestive health.

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

    The neuron detects numeric quantity tokens—especially measurements and amounts (e.g. grams, milligrams, calorie counts, percentages) in nutrition‐style data.

    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
    CPU
    -0.85
    ização
    -0.82
    隠し
    -0.79
    eggs
    -0.77
    Skate
    -0.75
    cotch
    -0.75
     قصة
    -0.75
    eurs
    -0.74
    izacion
    -0.74
    muster
    -0.74
    POSITIVE LOGITS
     fiber
    3.08
     fibre
    2.67
     Fiber
    2.58
    fiber
    2.44
    Fiber
    2.38
     Fibre
    2.30
     fibers
    2.19
     fibra
    2.09
    Fibre
    2.08
    fibre
    2.02
    Activations Density 0.031%

    No Known Activations