© 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. 81271
    Prev
    Next
    INDEX
    Explanations

    health and body conditions

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

    health and wellness topics, particularly information about nutrition, physical conditions, and medical treatments.

    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
    ﴿
    -0.94
    🤜
    -0.93
    HttpSession
    -0.93
    lois
    -0.88
    tout
    -0.87
    (&:
    -0.85
    trique
    -0.85
    werb
    -0.84
    စ်
    -0.83
    🍳
    -0.83
    POSITIVE LOGITS
     constitution
    0.97
     health
    0.90
     comprehensive
    0.83
     crowd
    0.82
    crowd
    0.81
     constitutions
    0.80
     physique
    0.79
     beauty
    0.79
     improve
    0.76
     cares
    0.76
    Activations Density 0.049%

    No Known Activations