© 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. 40212
    Prev
    Next
    INDEX
    Explanations

    file operations and imports

    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
    出来ました
    -1.00
    กลุ่ม
    -0.93
     egyes
    -0.93
    Για
    -0.92
    ピール
    -0.91
    είτε
    -0.90
     repudi
    -0.90
     移
    -0.89
    Зно
    -0.88
     aiuta
    -0.88
    POSITIVE LOGITS
     video
    1.23
     file
    1.14
     пальто
    1.13
     immagine
    1.13
    álise
    1.05
    nappropriate
    1.03
     manières
    1.00
    video
    0.98
     files
    0.95
     audio
    0.93
    Activations Density 0.069%

    No Known Activations