© 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. 16-GEMMASCOPE-2-RES-65K
    7. 876
    Prev
    Next
    INDEX
    Explanations

    business, finance, education, research, health

    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_16_width_65k_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
     vollständ
    0.63
     zwei
    0.62
     confusión
    0.62
     több
    0.61
     что
    0.61
     elettronica
    0.60
     മ
    0.60
     sehr
    0.60
     två
    0.60
     ühe
    0.60
    POSITIVE LOGITS
    x
    0.69
    al
    0.66
    in
    0.59
    i
    0.59
    ing
    0.55
    h
    0.55
    u
    0.52
    ↵
    0.50
    최
    0.49
     athletes
    0.47
    Activations Density 0.222%

    No Known Activations