© 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. 47517
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

    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
     as
    -2.27
     a
    -2.06
     because
    -2.03
     at
    -1.88
     which
    -1.67
     having
    -1.65
     some
    -1.65
     being
    -1.59
     from
    -1.59
     an
    -1.59
    POSITIVE LOGITS
    橚
    1.67
     jego
    1.66
    ſing
    1.54
    玊
    1.53
    ⇴
    1.53
    シンプルな
    1.52
    嘁
    1.49
     его
    1.48
     irmão
    1.45
    軽量
    1.44
    Activations Density 0.337%

    No Known Activations