© 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. 10-GEMMASCOPE-RES-131K
    4. 48517
    Prev
    Next
    INDEX
    Explanations

    various differences and classifications

    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
     by
    -1.84
     even
    -1.70
     it
    -1.58
     only
    -1.55
     two
    -1.51
     through
    -1.51
     both
    -1.50
     despite
    -1.47
     part
    -1.39
    !
    -1.38
    POSITIVE LOGITS
     olika
    1.77
     тях
    1.63
     différentes
    1.55
    穿搭
    1.49
    Their
    1.41
     поэтому
    1.39
     コットン
    1.39
    ⮑
    1.38
     разных
    1.36
     farklı
    1.36
    Activations Density 0.351%

    No Known Activations