© 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. 10-GEMMASCOPE-RES-131K
    7. 100783
    Prev
    Next
    INDEX
    Explanations

    scientists doing science

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

    references to scientists in academic or research contexts.

    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
     You
    -2.78
     Founded
    -2.48
     wayward
    -2.47
     Importantly
    -2.44
     austere
    -2.39
    ведения
    -2.38
    </h2>
    -2.36
     impec
    -2.30
     Whether
    -2.28
     มี
    -2.28
    POSITIVE LOGITS
    '
    2.83
     lyss
    2.58
    鸸
    2.52
    </i>
    2.50
     BRARY
    2.48
     插图
    2.45
     ナビ
    2.44
     ガイド
    2.42
    (;;)
    2.41
    歘
    2.39
    Activations Density 0.009%

    No Known Activations