© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 38656
    Prev
    Next
    INDEX
    Explanations

    weight loss diets

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

    words related to diets, nutrition, and eating patterns.

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

    The neuron is keyed to mentions of low-carbohydrate/ketogenic diet terminology (e.g. “low-carbohydrate,” “keto,” “Atkins Diet,” 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_22/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
     掃除
    -1.41
    龛
    -1.38
     パソコン
    -1.27
     дорого
    -1.24
    謚
    -1.23
     dollari
    -1.20
     правительства
    -1.17
     наличии
    -1.17
    ϳ
    -1.16
     quidem
    -1.15
    POSITIVE LOGITS
     ویتامین
    1.56
    ubwa
    1.52
     überweisen
    1.45
     אבל
    1.41
     cuillère
    1.40
     benzin
    1.36
     ܝ
    1.35
    IFESTYLE
    1.35
    bước
    1.34
    QUÉ
    1.34
    Activations Density 0.049%

    No Known Activations