© 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. 60277
    Prev
    Next
    INDEX
    Explanations

    By [verb]ing agreement

    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
     their
    -1.56
     first
    -1.47
     two
    -1.43
     as
    -1.39
     had
    -1.38
     three
    -1.36
     died
    -1.36
    但却
    -1.36
    "}")
    -1.35
     because
    -1.31
    POSITIVE LOGITS
    噐
    1.78
    妡
    1.71
    岨
    1.63
    ︲
    1.57
     verlie
    1.57
     OPPORTUNITIES
    1.53
    ዣ
    1.51
    盦
    1.46
    atürk
    1.46
    ATI
    1.45
    Activations Density 0.037%

    No Known Activations