© 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. 86816
    Prev
    Next
    INDEX
    Explanations

    state of satisfaction or conviction

    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
     différentes
    -1.66
     diferentes
    -1.63
     diversos
    -1.59
     vários
    -1.58
     verschillende
    -1.57
     différents
    -1.55
     ciudadanos
    -1.53
     infancia
    -1.46
     både
    -1.45
     semakin
    -1.43
    POSITIVE LOGITS
    There
    1.55
     when
    1.43
    这是什么
    1.41
     rằng
    1.41
    All
    1.40
    　　——
    1.36
    there
    1.29
    ၀
    1.25
    when
    1.24
     всю
    1.22
    Activations Density 0.013%

    No Known Activations