© 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. 8641
    Prev
    Next
    INDEX
    Explanations

    metadata keys like abstract, author

    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
     çünkü
    -1.95
     kwal
    -1.91
    っていたので
    -1.84
    !!!!!!!
    -1.82
     😁
    -1.82
     !!!!
    -1.81
     speciale
    -1.74
     italiens
    -1.73
     reaſon
    -1.70
     geene
    -1.70
    POSITIVE LOGITS
     while
    2.19
     more
    2.17
    Even
    2.03
     less
    2.00
     Even
    1.95
    Despite
    1.92
           
    1.89
    While
    1.84
    Although
    1.84
     although
    1.83
    Activations Density 0.012%

    No Known Activations