© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84365
    Prev
    Next
    INDEX
    Explanations

    healthy states or people

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

    The word "Healthy" at the beginning of phrases or titles, particularly in health, nutrition, and wellness contexts.

    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_10/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
    釤
    -2.92
     '
    -2.88
     ``
    -2.88
     horrifying
    -2.83
     ridiculously
    -2.77
     lauded
    -2.72
    锨
    -2.72
     .......
    -2.69
     เมื่อ
    -2.66
    漚
    -2.66
    POSITIVE LOGITS
    Even
    3.42
    With
    3.27
    Only
    3.19
    There
    3.09
    Without
    3.08
    0
    3.08
    It
    3.05
    Every
    2.98
    Several
    2.92
    While
    2.91
    Activations Density 0.008%

    No Known Activations