© 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. 86986
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    おわりに
    -1.16
    お待ち
    -1.08
    Teléfono
    -1.05
    ))[
    -1.03
    ܜ
    -1.02
    asinya
    -0.99
    ௰
    -0.99
     рішення
    -0.98
    の方に
    -0.98
    になりたい
    -0.98
    POSITIVE LOGITS
     halte
    1.02
    且
    0.97
    で
    0.96
    ↵
    0.96
    but
    0.90
    But
    0.88
    ziert
    0.88
    ```
    0.88
    的情况下
    0.87
    ่ง
    0.86
    Activations Density 0.018%

    No Known Activations