© 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. 22-GEMMASCOPE-RES-131K
    7. 70610
    Prev
    Next
    INDEX
    Explanations

    code assignments and names

    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_22/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
     now
    -1.55
     schreiben
    -1.26
    nutie
    -1.25
     falda
    -1.25
     just
    -1.23
    ONESIA
    -1.23
     компьютера
    -1.20
    会的
    -1.19
     also
    -1.18
    蚵
    -1.16
    POSITIVE LOGITS
    Fakta
    1.56
    Karakter
    1.44
    Кита
    1.36
     militer
    1.31
    Ilustra
    1.31
    Specifik
    1.30
    
    1.30
    臵
    1.26
     espelho
    1.26
     Эти
    1.25
    Activations Density 0.114%

    No Known Activations