© 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-16K
    7. 831
    Prev
    Next
    INDEX
    Explanations

    Newark location, daily aspirin, superconducting magnet

    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_16k_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
     வகையான
    0.32
    现在
    0.31
    \
    0.30
     或
    0.30
    _
    0.30
    =
    0.29
    q
    0.29
    [
    0.29
     utilisée
    0.29
    或
    0.29
    POSITIVE LOGITS
     مذکور
    0.37
    тник
    0.32
    лег
    0.31
     pihaknya
    0.30
     designee
    0.29
     patas
    0.29
     adhipp
    0.29
    Ꮞ
    0.29
    чик
    0.28
    тни
    0.28
    Activations Density 1.652%

    No Known Activations