© 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. 39400
    Prev
    Next
    INDEX
    Explanations

    microsatellite

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

    The neuron activates for words with the prefix "micro" or "micros" such as "microsatellite," "microsurgery," and "microscopic."

    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
     idyllic
    -2.36
    忤
    -2.23
     listos
    -2.14
     However
    -2.13
    睥
    -2.05
     Здесь
    -2.05
    外人
    -2.03
    퐼
    -2.02
     auch
    -2.00
     Here
    -1.99
    POSITIVE LOGITS
    the
    2.52
    The
    2.41
    </sub>
    2.31
    鼷
    2.28
    ༑
    2.25
    颙
    2.23
    ر
    2.22
    髙
    2.22
     cellule
    2.20
    "+
    2.20
    Activations Density 0.004%

    No Known Activations