© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5442
    Prev
    Next
    INDEX
    Explanations

    defining or determining

    np_acts-logits-general · gemini-2.5-flash-lite

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {\
    0.57
    """
    0.55
     {@
    0.54
     ```
    0.54
    ```
    0.52
     __
    0.48
     funcionalidades
    0.48
     ->
    0.47
         
    0.46
    ",
    0.46
    POSITIVE LOGITS
     Define
    0.50
     endregion
    0.49
     Defining
    0.47
    defining
    0.46
     定义
    0.45
     определя
    0.45
    ફેદ
    0.44
    наче
    0.44
    endregion
    0.43
     defining
    0.43
    Activations Density 0.001%

    No Known Activations