© 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. 70574
    Prev
    Next
    INDEX
    Explanations

    code, programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    こんばん
    -1.66
    宮崎
    -1.66
    はじめまして
    -1.65
    投稿日
    -1.53
    e
    -1.52
     Rückseite
    -1.49
     my
    -1.41
    ”,
    -1.37
    ハワイ
    -1.37
     (‘
    -1.36
    POSITIVE LOGITS
     of
    2.48
    .
    1.73
     étaient
    1.41
     appunt
    1.38
     Também
    1.37
     Daarom
    1.36
    颪
    1.33
     Pokud
    1.30
     Rabu
    1.29
    träglich
    1.28
    Activations Density 0.001%

    No Known Activations