© 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. 100591
    Prev
    Next
    INDEX
    Explanations

    official roles and technical terms

    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
     ijs
    -1.68
     goud
    -1.61
     meren
    -1.59
     geel
    -1.55
    “”
    -1.55
     nime
    -1.55
     kado
    -1.54
    
    -1.51
     datter
    -1.50
     ſta
    -1.48
    POSITIVE LOGITS
     With
    1.94
    While
    1.78
    There
    1.77
    With
    1.77
    Since
    1.71
    Some
    1.62
    During
    1.61
    Every
    1.58
    四月
    1.57
    Before
    1.55
    Activations Density 0.077%

    No Known Activations