© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123542
    Prev
    Next
    INDEX
    Explanations

    Zika virus, Raspberry Pi, AGA

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

    brand names and disease names, particularly recognizing brands like "Zara" and viruses like "Zika."

    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
    鯢
    -2.58
    鱻
    -2.44
    を使用した
    -2.23
    眚
    -2.20
    泐
    -2.19
     dévelo
    -2.19
    檠
    -2.19
    performs
    -2.17
    ⏑
    -2.17
     splend
    -2.16
    POSITIVE LOGITS
     aktiven
    2.58
     frühen
    2.34
     wichtigen
    2.33
     täglichen
    2.31
     gewiß
    2.27
    Some
    2.25
    Those
    2.20
     speziellen
    2.19
    ПИ
    2.17
     offenen
    2.16
    Activations Density 0.010%

    No Known Activations