© 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. 34-GEMMASCOPE-RES-131K
    7. 90692
    Prev
    Next
    INDEX
    Explanations

    status code method type

    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_34/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
     粉色
    -1.18
     аксессу
    -1.18
     relojes
    -1.17
     rijden
    -1.13
     път
    -1.11
     кухо
    -1.09
    ₁(
    -1.09
    pantalon
    -1.09
     baterie
    -1.06
     postales
    -1.06
    POSITIVE LOGITS
    风的
    1.10
    这两个
    0.98
    它们的
    0.98
     immaculate
    0.98
     بتوان
    0.93
     wenigstens
    0.92
     trasforma
    0.91
    馀
    0.91
     golden
    0.90
     facendo
    0.88
    Activations Density 0.040%

    No Known Activations