© 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. 64332
    Prev
    Next
    INDEX
    Explanations

    zoo and zoological parks

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

    references to zoos, wildlife parks, and animal facilities.

    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
     zdję
    -0.75
     Fahrrad
    -0.73
     čer
    -0.69
    closet
    -0.68
     labores
    -0.68
    thodes
    -0.66
    rural
    -0.66
     dog
    -0.66
    ollett
    -0.66
    と思っていた
    -0.66
    POSITIVE LOGITS
     zoo
    4.34
     Zoo
    3.94
    Zoo
    3.58
     zoos
    3.31
    zoo
    3.25
     Zoological
    2.42
     Zo
    2.14
    動物園
    2.11
    Zo
    2.00
     зо
    1.99
    Activations Density 0.040%

    No Known Activations