© 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. 124090
    Prev
    Next
    INDEX
    Explanations

    in this paper we

    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
     in
    -1.59
     if
    -1.49
     themselves
    -1.45
     for
    -1.39
     he
    -1.38
     tvá
    -1.34
     of
    -1.33
    罅
    -1.30
    jdons
    -1.30
     автоном
    -1.29
    POSITIVE LOGITS
    䛗
    1.65
     diza
    1.64
     jaket
    1.62
    齪
    1.60
     merce
    1.59
    
    1.55
     useAppContext
    1.54
    ENED
    1.54
     sains
    1.54
    お知らせ
    1.53
    Activations Density 0.115%

    No Known Activations