© 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. 74886
    Prev
    Next
    INDEX
    Explanations

    language codes and translation markers

    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
     ограничения
    -1.01
     dłu
    -0.94
     our
    -0.93
     czemu
    -0.90
    licitud
    -0.88
     нашей
    -0.88
    おわりに
    -0.86
     those
    -0.85
    tionally
    -0.85
     leitet
    -0.84
    POSITIVE LOGITS
     Substan
    1.06
     насеља
    0.99
    Ѳ
    0.96
     cães
    0.96
    寻常
    0.95
     ورزشی
    0.95
    涿
    0.94
     öffnungszeiten
    0.94
    俟
    0.94
    MQTT
    0.93
    Activations Density 0.003%

    No Known Activations