© 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. 106802
    Prev
    Next
    INDEX
    Explanations

    Sturgeon Bay, stent migration

    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
     wanted
    -0.94
    скус
    -0.85
    려
    -0.82
     باشند
    -0.81
     умова
    -0.80
     descansar
    -0.79
    ดิ
    -0.79
     Freiw
    -0.74
    ctividad
    -0.73
     started
    -0.73
    POSITIVE LOGITS
     st
    1.16
     St
    1.02
    ViewById
    0.96
     '[
    0.93
     creo
    0.86
    婊
    0.85
    UUUU
    0.84
     "{
    0.83
     '^
    0.83
     Lucía
    0.82
    Activations Density 0.049%

    No Known Activations