© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158433
    Prev
    Next
    INDEX
    Explanations

    Turkish language and writing

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

    titles and academic terms

    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_31_width_262k_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
     ech
    0.54
     parentheses
    0.53
     GAA
    0.51
     refrigerators
    0.50
     wardrobe
    0.50
     accessories
    0.49
     blat
    0.49
     i
    0.49
     tiles
    0.49
     handbags
    0.49
    POSITIVE LOGITS
    ```{
    0.53
    밖
    0.47
    破坏
    0.46
    著作
    0.46
    绢
    0.46
    解釋
    0.46
    論文
    0.45
    ی
    0.44
    세
    0.44
    の研究
    0.44
    Activations Density 0.001%

    No Known Activations