© 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. 58966
    Prev
    Next
    INDEX
    Explanations

    family pedigree relationships

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

    text related to family relationships, genetics, and genealogy research.

    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
    品牌
    -0.96
    emplos
    -0.85
     burs
    -0.83
    明け
    -0.81
     homeward
    -0.80
     nestled
    -0.79
     Konto
    -0.79
    водитель
    -0.78
    řit
    -0.78
     metallo
    -0.75
    POSITIVE LOGITS
     marriage
    1.10
     relationship
    1.09
     patriarch
    1.08
     family
    1.08
     relationships
    1.06
     pedigree
    1.04
     children
    1.03
     deceased
    0.98
    individuals
    0.96
     Relationship
    0.95
    Activations Density 0.037%

    No Known Activations