© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22131
    Prev
    Next
    INDEX
    Explanations

    xml namespace declarations

    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
     blissful
    -1.88
    {~
    -1.80
    mathrm
    -1.76
     типу
    -1.70
     sparkly
    -1.70
     його
    -1.66
    ”，
    -1.66
    asyonu
    -1.66
     .....
    -1.64
     blistering
    -1.64
    POSITIVE LOGITS
    
    2.13
     doen
    2.11
    primarily
    2.09
    mainly
    1.95
    within
    1.89
    㩒
    1.89
    really
    1.84
    many
    1.84
    ﹍﹍
    1.83
     イラストレーション
    1.78
    Activations Density 0.001%

    No Known Activations