© 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. 67328
    Prev
    Next
    INDEX
    Explanations

    introducing statements

    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
     также
    -1.60
     during
    -1.38
     również
    -1.34
     yaitu
    -1.29
     различные
    -1.28
     crescere
    -1.27
    ִּ
    -1.21
     tersebut
    -1.20
     آن‌ها
    -1.20
    was
    -1.18
    POSITIVE LOGITS
     you
    1.94
     lantaran
    1.28
     hitherto
    1.27
    Aquí
    1.22
    Imágenes
    1.19
     utterly
    1.16
    >=
    1.15
     aşağı
    1.15
     вполне
    1.14
    Кстати
    1.14
    Activations Density 0.031%

    No Known Activations