© 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-65K
    7. 39801
    Prev
    Next
    INDEX
    Explanations

    mathematical embeddings

    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_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
     некоторые
    0.47
    一些
    0.44
    ane
    0.43
    ying
    0.43
    ilib
    0.42
     ಹಲವಾರು
    0.41
    ח
    0.40
    VO
    0.40
    िश्चित
    0.40
    ol
    0.39
    POSITIVE LOGITS
     pięk
    0.52
     Layer
    0.48
     foams
    0.46
     Weddings
    0.46
     raison
    0.44
     bicovariant
    0.43
     cohom
    0.43
     czyli
    0.43
     Dès
    0.43
     cohorts
    0.42
    Activations Density 0.019%

    No Known Activations