© 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. 47720
    Prev
    Next
    INDEX
    Explanations

    historical dates and regions

    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
    嵓
    -1.69
    んでも
    -1.53
    
    -1.48
     perpé
    -1.45
     vider
    -1.39
     barnet
    -1.38
     venter
    -1.38
    .
    -1.38
    倏
    -1.36
     bont
    -1.33
    POSITIVE LOGITS
     from
    1.54
    𓂂
    1.25
     sentido
    1.25
     abogados
    1.23
     ň
    1.22
    =>{
    1.21
    ftance
    1.20
     toàn
    1.17
     as
    1.16
    ان
    1.16
    Activations Density 0.118%

    No Known Activations