© 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. 72888
    Prev
    Next
    INDEX
    Explanations

    hired professionals

    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
    sowie
    -1.38
    -¡
    -1.34
    Kedves
    -1.31
    Sekolah
    -1.30
    Fotó
    -1.27
    Kesimpulan
    -1.27
     felhasznál
    -1.27
    
    -1.27
    Liefer
    -1.26
     kritik
    -1.26
    POSITIVE LOGITS
     to
    2.14
     or
    2.05
     is
    1.76
     who
    1.62
     when
    1.59
     if
    1.55
     what
    1.43
     before
    1.41
     there
    1.39
     will
    1.38
    Activations Density 0.089%

    No Known Activations