© 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. 123782
    Prev
    Next
    INDEX
    Explanations

    I know / I suppose

    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
     "
    -1.88
     especialmente
    -1.48
    露出了
    -1.47
    ísa
    -1.39
    ("");
    
    -1.38
    YNAMIC
    -1.38
     mostrarse
    -1.31
    神情
    -1.30
    :[
    -1.30
     ''
    -1.28
    POSITIVE LOGITS
     have
    1.59
     problems
    1.29
    ,
    1.24
     orice
    1.23
     biodivers
    1.20
    梦见
    1.15
     sigu
    1.14
     estim
    1.13
     캐릭터
    1.12
     भी
    1.09
    Activations Density 0.066%

    No Known Activations