© 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. 34-GEMMASCOPE-RES-131K
    7. 57976
    Prev
    Next
    INDEX
    Explanations

    health and safety concepts

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

    the phrase "health and" in healthcare 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_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
     diplôme
    -0.93
    近年来
    -0.86
     hashtags
    -0.86
    ハワイ
    -0.85
     Undeclared
    -0.84
    saturday
    -0.84
    tellten
    -0.84
     réalisation
    -0.83
     heerlijk
    -0.82
    Җ
    -0.82
    POSITIVE LOGITS
     wellness
    2.03
     wellbeing
    1.63
     fitness
    1.55
     safety
    1.49
     welfare
    1.37
     health
    1.32
     Wellness
    1.27
     Safety
    1.15
     happiness
    1.13
     well
    1.11
    Activations Density 0.022%

    No Known Activations