© 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. 10-GEMMASCOPE-RES-131K
    7. 123514
    Prev
    Next
    INDEX
    Explanations

    aquarium, geography, life science terms

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

    terms and concepts related to aquarium keeping and aquatic life.

    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_10/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
    וּ
    -1.63
    וּ
    -1.62
     after
    -1.59
    ּוֹ
    -1.49
     zelfs
    -1.48
     should
    -1.45
     различни
    -1.40
     After
    -1.37
     aldus
    -1.37
     технологі
    -1.35
    POSITIVE LOGITS
    ׇ
    1.95
     النبات
    1.80
     сахара
    1.60
     botanique
    1.59
     cukru
    1.58
    ₱
    1.55
     roś
    1.55
     ویتامین
    1.52
    ੲ
    1.51
    velser
    1.43
    Activations Density 0.058%

    No Known Activations