© 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. 10-GEMMASCOPE-RES-131K
    7. 952
    Prev
    Next
    INDEX
    Explanations

    code patterns and function calls

    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_10/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
    flexGrow
    -1.77
     mereka
    -1.72
    Both
    -1.67
    Two
    -1.55
    Before
    -1.55
     Both
    -1.45
     сказать
    -1.45
    Three
    -1.43
     назвать
    -1.42
     and
    -1.41
    POSITIVE LOGITS
    茕
    1.98
     necessário
    1.72
     nación
    1.63
    ://$
    1.61
     <>",
    1.61
    itattu
    1.52
    ⚣
    1.45
     <",
    1.45
     was
    1.43
     dictadura
    1.41
    Activations Density 0.017%

    No Known Activations