© 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. 59977
    Prev
    Next
    INDEX
    Explanations

    avoid sugar, alcohol, caffeine, and fat

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

    dietary advice about what to avoid in food and drinks.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    DEPART
    -0.88
     asma
    -0.84
    малар
    -0.82
    ʡ
    -0.82
     conscience
    -0.79
     masih
    -0.78
     प्रदान
    -0.77
     hipo
    -0.77
    འི་
    -0.77
     monstru
    -0.77
    POSITIVE LOGITS
     alcohol
    1.88
     caffeine
    1.40
    Alcohol
    1.34
    alcohol
    1.31
     processed
    1.28
     coffee
    1.28
     Alcohol
    1.27
     refined
    1.23
     alkoholu
    1.22
     spicy
    1.21
    Activations Density 0.032%

    No Known Activations