© 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. 116933
    Prev
    Next
    INDEX
    Explanations

    health or medical terms

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

    content related to medical information and health protective measures.

    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
    Ironically
    -0.91
     Ironically
    -0.85
     in
    -0.85
    Drilling
    -0.85
     stately
    -0.85
     tiny
    -0.85
     demanded
    -0.84
     at
    -0.84
     some
    -0.84
     five
    -0.81
    POSITIVE LOGITS
    rinfo
    1.09
    "=>
    1.07
    ícios
    1.02
    ktioner
    1.00
    oleic
    0.99
     inconsist
    0.99
    ність
    0.97
    mlen
    0.97
    ļi
    0.96
     decedent
    0.95
    Activations Density 0.013%

    No Known Activations