© 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. 34-GEMMASCOPE-RES-131K
    7. 64806
    Prev
    Next
    INDEX
    Explanations

    ants and colonies

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

    taxonomic or scientific descriptions of ants and other insects.

    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
     ρο
    -0.95
     waterfowl
    -0.76
     پسر
    -0.76
     SPORT
    -0.73
     Sport
    -0.71
     lur
    -0.69
     vũ
    -0.69
     sport
    -0.69
    tut
    -0.68
     gubern
    -0.68
    POSITIVE LOGITS
     ants
    1.68
     Ants
    1.41
     worker
    1.39
     workers
    1.29
     queen
    1.28
     colony
    1.27
     queens
    1.27
     colonies
    1.25
     ant
    1.20
     nest
    1.14
    Activations Density 0.030%

    No Known Activations