© 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. 74882
    Prev
    Next
    INDEX
    Explanations

    package names or code imports

    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
     प्रोड
    -1.42
     टॉप
    -1.23
     स्क्रीन
    -1.18
    ׇ
    -1.16
     since
    -1.09
     where
    -1.09
     feels
    -1.08
     الشاشة
    -1.06
     Bereiche
    -1.06
    asyarakat
    -1.05
    POSITIVE LOGITS
    brtc
    1.33
    Menurutnya
    1.24
    збе
    1.19
     лишь
    1.16
    ffilm
    1.14
    смарт
    1.13
    нівер
    1.11
    zzet
    1.10
     должен
    1.09
    IonicModule
    1.09
    Activations Density 0.000%

    No Known Activations