© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67560
    Prev
    Next
    INDEX
    Explanations

    fasting and food restriction

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

    content related to fasting and dietary restrictions.

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

    This neuron activates on references to fasting—that is, words and phrases indicating a “fast” or “fasting” period.

    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
    Rede
    -0.93
     consideran
    -0.86
     lube
    -0.85
    گون
    -0.85
    apr
    -0.85
     Gottes
    -0.84
    ostí
    -0.84
     Farbe
    -0.82
     the
    -0.82
    B
    -0.82
    POSITIVE LOGITS
     diet
    1.16
     imposed
    1.10
     RequestMethod
    1.03
    เพื่อ
    1.03
    jugend
    1.02
     for
    1.02
    ])){
    0.99
     fasting
    0.98
    อาหาร
    0.98
    espejo
    0.98
    Activations Density 0.077%

    No Known Activations