© 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. 48726
    Prev
    Next
    INDEX
    Explanations

    worker bees

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

    content related to bees, especially discussing honey bees, queens, and colony structure.

    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
    ionado
    -0.96
     compressor
    -0.77
     Estudiantes
    -0.75
    煕
    -0.74
     STRATEGY
    -0.74
    Serialize
    -0.74
    ිය
    -0.74
    schutz
    -0.73
     soorten
    -0.72
     chịu
    -0.72
    POSITIVE LOGITS
     worker
    1.39
     workers
    1.34
     Worker
    1.08
     brood
    1.07
    worker
    1.02
     royal
    0.98
    workers
    0.93
    Worker
    0.93
    royal
    0.90
    Workers
    0.90
    Activations Density 0.030%

    No Known Activations