© 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. 20301
    Prev
    Next
    INDEX
    Explanations

    php code

    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
    
    -2.36
    
    -2.27
    喾
    -2.13
     asegurado
    -2.09
     mantenido
    -2.06
     alcanzado
    -2.06
    蕻
    -2.05
    ſelves
    -1.99
     motivadoras
    -1.98
    Gentile
    -1.98
    POSITIVE LOGITS
     xxii
    2.30
    ly
    2.30
    when
    2.27
    Please
    2.22
    Is
    2.20
    {
    2.17
     xxiii
    2.17
    塒
    2.14
    褙
    2.11
    Which
    2.09
    Activations Density 0.043%

    No Known Activations