© 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. 34-GEMMASCOPE-RES-131K
    4. 86878
    Prev
    Next
    INDEX
    Explanations

    permissions to do

    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
    ьере
    -0.81
    れません
    -0.81
    编号
    -0.79
     frugal
    -0.79
     diamantes
    -0.78
    不存在
    -0.77
     pepe
    -0.77
    布局
    -0.77
     chino
    -0.76
     Mademoiselle
    -0.76
    POSITIVE LOGITS
    uot
    0.90
     ComVisible
    0.88
    interesting
    0.85
     aconteceu
    0.85
     indicaciones
    0.83
    happen
    0.81
    cels
    0.79
    ével
    0.79
     typelib
    0.79
    넓
    0.79
    Activations Density 0.004%

    No Known Activations