© 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. 39623
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and Greek letters

    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
     daha
    -1.22
     glyphicon
    -1.21
     Méd
    -1.20
     karde
    -1.20
     senin
    -1.19
    ⬇️
    -1.19
     ido
    -1.18
    Ｗ
    -1.17
    下意识
    -1.16
     argentino
    -1.15
    POSITIVE LOGITS
    ’
    1.52
     a
    1.41
     each
    1.25
     невели
    1.14
     Эти
    1.13
     equilíbrio
    1.10
     these
    1.06
    多谢
    1.05
     treinamento
    1.04
     Decrease
    1.03
    Activations Density 0.012%

    No Known Activations