© 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. 10826
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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
    Jum
    -1.11
    Ruj
    -1.03
    Rij
    -0.98
    BIOGRAPHY
    -0.94
     lezioni
    -0.94
    Livre
    -0.93
     fonti
    -0.93
    Vra
    -0.93
     シャツ
    -0.91
     constater
    -0.90
    POSITIVE LOGITS
     where
    1.33
     at
    1.03
     où
    0.93
     favoritas
    0.92
    邃
    0.91
    --;
    
    0.90
    ⏳
    0.88
     it
    0.87
    érieurs
    0.86
     veinte
    0.86
    Activations Density 0.020%

    No Known Activations