© 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. 75714
    Prev
    Next
    INDEX
    Explanations

    `uint` type and struct definitions

    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
    铙
    -1.55
    肯定会
    -1.48
     Fahren
    -1.48
    somewhat
    -1.48
    一旁
    -1.46
    飾り
    -1.46
    {{-
    -1.45
    tit
    -1.42
    OU
    -1.42
    ..."
    -1.41
    POSITIVE LOGITS
     of
    2.31
     or
    2.14
    These
    1.70
     تجمعات
    1.54
    んですが
    1.49
     meestal
    1.48
     они
    1.43
    ～！
    1.42
    んですね
    1.41
     весна
    1.41
    Activations Density 0.002%

    No Known Activations