© 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. 90427
    Prev
    Next
    INDEX
    Explanations

    mathematical set notation

    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
     also
    -1.70
    瞑
    -1.56
    ↵
    -1.41
     и
    -1.38
     seleccionamos
    -1.36
    meldet
    -1.36
     aurait
    -1.30
                
    -1.30
     still
    -1.29
     своих
    -1.29
    POSITIVE LOGITS
    こんな
    1.70
     kurie
    1.66
    コロナ禍
    1.57
    ChrTalk
    1.56
    ここ
    1.52
    ⬮
    1.52
    '],$
    1.50
    ㈰
    1.48
    cisive
    1.45
    「
    1.42
    Activations Density 0.011%

    No Known Activations