© 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. 123819
    Prev
    Next
    INDEX
    Explanations

    antiviral drug or agent

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

    technical abbreviations and acronyms related to computing, technology, and medical fields.

    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
     pittores
    -2.72
    艄
    -2.64
     actes
    -2.52
    A
    -2.44
     撮っ
    -2.44
     caricatura
    -2.41
     tuta
    -2.39
    鶫
    -2.39
    回来的
    -2.38
    强行
    -2.38
    POSITIVE LOGITS
     They
    3.38
     In
    3.02
     If
    2.98
     Of
    2.78
    一部分
    2.75
     averiguar
    2.61
     Also
    2.61
     There
    2.59
     herhangi
    2.55
     While
    2.47
    Activations Density 0.001%

    No Known Activations