© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71709
    Prev
    Next
    INDEX
    Explanations

    git diff header

    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
    btnCancel
    -1.12
    了两
    -1.09
     doba
    -1.07
    Jueves
    -1.06
     calitate
    -1.05
     rádio
    -1.04
    análisis
    -1.04
     mendapatkan
    -1.02
    тости
    -1.02
     būs
    -1.00
    POSITIVE LOGITS
     действие
    0.92
     таким
    0.88
    ⅙
    0.88
    о
    0.87
    金额
    0.85
    ⅖
    0.85
     seconds
    0.85
    aff
    0.84
    .</
    0.84
     домов
    0.84
    Activations Density 0.001%

    No Known Activations