© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102844
    Prev
    Next
    INDEX
    Explanations

    foreign words, programming, science

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

    acronyms or abbreviations in technical and professional contexts, particularly those containing "AT" within them.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     and
    -1.98
     to
    -1.81
     dokonce
    -1.57
    倏
    -1.51
    摇了
    -1.48
    悄悄
    -1.45
    勿論
    -1.41
    遠慮
    -1.41
     my
    -1.41
     is
    -1.41
    POSITIVE LOGITS
     manteau
    1.69
    𓆜
    1.66
     sonno
    1.63
    夘
    1.63
     inoxid
    1.56
    衕
    1.54
     specchio
    1.51
    今天
    1.50
    leistungen
    1.48
     vêtements
    1.48
    Activations Density 0.001%

    No Known Activations