© 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. 34-GEMMASCOPE-RES-131K
    7. 31459
    Prev
    Next
    INDEX
    Explanations

    Proper names and locations

    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_34/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
    ksessa
    -0.85
     יִ
    -0.79
     הָ
    -0.77
    ตน
    -0.75
    景观
    -0.73
     сили
    -0.73
     Trinidad
    -0.73
    ători
    -0.73
     зарубе
    -0.73
     Airtel
    -0.71
    POSITIVE LOGITS
    aragus
    0.89
     connects
    0.79
     обна
    0.75
     长
    0.73
     mieszkańców
    0.72
    竅
    0.71
     thoát
    0.70
    SuspendLayout
    0.70
     ligar
    0.70
     refiere
    0.69
    Activations Density 0.012%

    No Known Activations