© 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. 48608
    Prev
    Next
    INDEX
    Explanations

    code and document structure

    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
     preprint
    0.62
    arXiv
    0.57
     Preprint
    0.56
     arXiv
    0.55
    T
    0.54
    Dirac
    0.52
     Dirac
    0.51
     LaTeX
    0.51
     \
    0.51
     Theorem
    0.50
    POSITIVE LOGITS
     ресторан
    0.54
     oysters
    0.51
     negócios
    0.51
     bateau
    0.49
     foodie
    0.49
     caza
    0.49
     houseboat
    0.49
     নৌকা
    0.48
     planificación
    0.48
     planejamento
    0.48
    Activations Density 0.003%

    No Known Activations