© 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. 12531
    Prev
    Next
    INDEX
    Explanations

    indicates then consequence

    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
     火锅
    -1.01
    🦎
    -0.99
    himo
    -0.94
     bandung
    -0.93
     parang
    -0.93
    Sair
    -0.92
     vitamine
    -0.91
     també
    -0.90
     automobili
    -0.88
        
    -0.88
    POSITIVE LOGITS
     then
    1.55
     indicates
    1.45
     indicate
    1.42
     indicating
    1.32
    Then
    1.08
     meist
    1.06
     indication
    1.06
    说明
    1.02
     tức
    1.02
    indicates
    1.02
    Activations Density 0.021%

    No Known Activations