© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41089
    Prev
    Next
    INDEX
    Explanations

    preceding specific nouns

    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
     آن‌ها
    -1.48
    ⩴
    -1.45
    可能是
    -1.45
    可能
    -1.45
     zoude
    -1.41
    卺
    -1.40
    痪
    -1.38
     atyp
    -1.35
    )|^{
    -1.34
    秆
    -1.34
    POSITIVE LOGITS
     in
    1.63
     any
    1.62
     some
    1.62
     numerous
    1.62
     many
    1.59
     two
    1.56
     three
    1.55
     around
    1.55
     most
    1.55
     four
    1.55
    Activations Density 0.277%

    No Known Activations