© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28617
    Prev
    Next
    INDEX
    Explanations

    ; import

    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_22/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
    breviations
    -0.99
     begins
    -0.97
     fjor
    -0.95
    已是
    -0.92
    gems
    -0.92
    ”？
    -0.90
    شناسی
    -0.88
    EventArgs
    -0.87
    tening
    -0.87
     contains
    -0.86
    POSITIVE LOGITS
    ↵↵
    1.20
     ervoor
    1.01
    の結果
    0.93
     cuantos
    0.92
     рынке
    0.92
    madı
    0.92
    ୨
    0.91
     comunque
    0.90
    یدا
    0.87
     daarbij
    0.87
    Activations Density 0.002%

    No Known Activations