© 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. 117955
    Prev
    Next
    INDEX
    Explanations

    healthy states and behaviors

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

    The neuron identifies words and phrases related to health and wellness, particularly the word "healthy" followed by different contexts like "eating," "people," "planet," or "ageing."

    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
    </strong>
    -0.98
    vov
    -0.89
     ``
    -0.88
     comenta
    -0.88
    受害
    -0.87
     защиты
    -0.86
     hardships
    -0.85
     festivities
    -0.83
     petty
    -0.82
     sağlık
    -0.82
    POSITIVE LOGITS
     eating
    1.18
     gums
    1.08
     habits
    1.06
    TOKYO
    1.05
     skepticism
    1.02
     беременности
    1.02
     جيدة
    1.00
     competition
    0.99
     living
    0.98
     kebiasaan
    0.98
    Activations Density 0.029%

    No Known Activations