© 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. 90295
    Prev
    Next
    INDEX
    Explanations

    health and illness conditions

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

    biographical information about a person's life changes, health issues, or career transitions.

    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
    bourhood
    -0.88
    tette
    -0.84
     भे
    -0.81
    itinéraire
    -0.80
     cytoplas
    -0.80
    便秘
    -0.79
     bunun
    -0.78
     userService
    -0.77
     drm
    -0.77
     mutagenicity
    -0.76
    POSITIVE LOGITS
     health
    3.59
     illness
    3.33
    health
    2.55
     illnesses
    2.47
     disease
    2.45
     cancer
    2.45
     sickness
    2.42
     Health
    2.28
    Health
    2.22
     diseases
    2.19
    Activations Density 0.079%

    No Known Activations