© 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. 3735
    Prev
    Next
    INDEX
    Explanations

    block diagram

    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
     When
    -2.70
     There
    -2.34
     With
    -2.16
    There
    -2.14
     Whenever
    -2.11
    When
    -2.09
     Even
    -2.06
    Even
    -1.95
    你可以
    -1.94
     Those
    -1.89
    POSITIVE LOGITS
     of
    2.05
     continually
    1.91
     is
    1.85
    읖
    1.81
    嚅
    1.77
     largely
    1.75
     réfugiés
    1.73
    0
    1.73
     ſont
    1.71
     somewhat
    1.69
    Activations Density 0.019%

    No Known Activations