© 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. 111092
    Prev
    Next
    INDEX
    Explanations

    vitamins, protein, nutrients

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

    descriptions of nutritional content, particularly when listing vitamins, minerals, and nutrients.

    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
    []
    -0.92
    cosx
    -0.89
    مزید
    -0.87
    СТВА
    -0.85
    pecker
    -0.84
    鹄
    -0.82
    "=
    -0.81
    徳島
    -0.81
    ]>
    -0.81
    🖕
    -0.80
    POSITIVE LOGITS
     protein
    2.03
     Vitamin
    1.83
     proteins
    1.73
     Protein
    1.68
     calcium
    1.67
     iron
    1.66
     vitamin
    1.65
     omega
    1.65
     vitamins
    1.63
     Omega
    1.58
    Activations Density 0.066%

    No Known Activations