© 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. 9275
    Prev
    Next
    INDEX
    Explanations

    Merck & Co

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

    References to Microsoft or Microsoft-related products, particularly Merck, MSD, and MSDN.

    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
    でしたが
    -2.86
    になりますが
    -2.34
     möglichen
    -2.34
     preciosas
    -2.23
     Bedürfn
    -2.22
     myriad
    -2.22
     faldas
    -2.19
     
    -2.14
     tomado
    -2.14
     pestañas
    -2.09
    POSITIVE LOGITS
    o
    2.58
     '';
    2.41
    ,
    2.34
    k
    2.28
    n
    2.22
    ),
    2.19
    oğlu
    2.11
    汌
    2.06
    がる
    2.05
     giocatori
    2.05
    Activations Density 0.003%

    No Known Activations