© 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. 66005
    Prev
    Next
    INDEX
    Explanations

    Sir Walter, Sir Frank, Toronto Blue, Tokyo MX

    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
    从来没有
    -1.52
    actéristi
    -1.48
     bateaux
    -1.34
    놋
    -1.34
     continuant
    -1.30
    
    -1.29
     soixante
    -1.27
     précédentes
    -1.27
     oogen
    -1.27
     -
    -1.23
    POSITIVE LOGITS
     both
    1.72
     that
    1.70
     by
    1.67
     Even
    1.58
     with
    1.55
     referirse
    1.51
     even
    1.48
     How
    1.47
     With
    1.47
     Although
    1.45
    Activations Density 0.112%

    No Known Activations