© 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. 10-GEMMASCOPE-RES-131K
    7. 84001
    Prev
    Next
    INDEX
    Explanations

    health and nutrition research

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

    scientific content related to nutritional studies, particularly measurements related to diet, health indices, and laboratory experiments.

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

    The neuron detects mentions of named quantitative indexes or measurement tools (e.g. “Eating Choices Index,” “diet quality index,” survey scores, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     hôtels
    -1.15
     importanti
    -1.13
     ?";
    -1.12
    インストール
    -1.12
    キーボード
    -1.11
     ſuch
    -1.10
    ος
    -1.10
    Ɩ
    -1.09
     to
    -1.09
     rivales
    -1.08
    POSITIVE LOGITS
     food
    1.52
     guidelines
    1.43
    ubwa
    1.38
     modifications
    1.38
     Food
    1.32
     Wednesday
    1.32
    kunci
    1.31
     changes
    1.30
     change
    1.30
     by
    1.28
    Activations Density 1.172%

    No Known Activations