© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38851
    Prev
    Next
    INDEX
    Explanations

    people with medical conditions or disabilities

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

    descriptions of vulnerable populations including disabled, ill, elderly, or minority individuals.

    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_22/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
     to
    -1.51
      
    -1.48
       
    -1.38
     wooded
    -1.30
          
    -1.30
     något
    -1.29
    u
    -1.24
    -1.22
    IDs
    -1.21
     wichtigen
    -1.21
    POSITIVE LOGITS
     people
    2.70
     who
    2.41
     individuals
    2.20
     persons
    1.88
     Pristup
    1.57
     person
    1.53
     folks
    1.50
     εκεί
    1.50
     черные
    1.48
     budete
    1.46
    Activations Density 0.163%
    No Known Activations