© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101428
    Prev
    Next
    INDEX
    Explanations

    text processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     цветы
    0.46
    袤
    0.45
    мен
    0.45
    казать
    0.43
     показать
    0.42
     себе
    0.42
    Я
    0.41
    いを
    0.40
     चाहें
    0.40
     написать
    0.40
    POSITIVE LOGITS
     encountered
    0.50
     preval
    0.47
     encountering
    0.47
     experiencing
    0.47
     clinicians
    0.44
    encountered
    0.42
     interfaces
    0.42
     affer
    0.42
     subpopulations
    0.42
    fps
    0.41
    Activations Density 0.003%

    No Known Activations