© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1814
    Prev
    Next
    INDEX
    Explanations

    substrings, sublists, subtrees

    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
     doubl
    -1.41
    âncias
    -1.41
    ciutto
    -1.38
    ynek
    -1.38
    figer
    -1.38
     ABBREVIATIONS
    -1.37
    幢
    -1.35
    轮胎
    -1.34
     подоб
    -1.31
    жении
    -1.30
    POSITIVE LOGITS
    (
    1.86
     that
    1.79
    <bos>
    1.75
    :
    1.68
    3
    1.66
    [
    1.62
     Ensuring
    1.56
    。
    1.46
     Each
    1.46
     of
    1.45
    Activations Density 0.034%

    No Known Activations