© 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. 73385
    Prev
    Next
    INDEX
    Explanations

    aquatic and marine wildlife

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

    text about wildlife, particularly focusing on birds, animals, and their environmental conditions.

    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
    뜬
    -0.91
     الطب
    -0.81
     slä
    -0.80
     onOptions
    -0.79
     lyck
    -0.79
    unchecked
    -0.78
    JOSEPH
    -0.77
     المقبل
    -0.77
    蚵
    -0.76
     impart
    -0.75
    POSITIVE LOGITS
     birds
    1.55
     wildlife
    1.48
    birds
    1.04
     fauna
    1.02
     organisms
    1.02
     populations
    1.02
     indicator
    0.97
     animals
    0.96
     plants
    0.95
     resident
    0.93
    Activations Density 0.100%

    No Known Activations