© 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. 56251
    Prev
    Next
    INDEX
    Explanations

    Binet, LangChain, Lumiflora, Vaadin, VS Code, F-35

    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
    3
    0.59
    s
    0.59
    ↵
    0.58
    el
    0.56
     in
    0.54
    य
    0.54
    Depois
    0.52
    ב
    0.51
    ing
    0.50
     and
    0.49
    POSITIVE LOGITS
    ższ
    0.49
    oksatta
    0.47
    jenigen
    0.46
     ఎక్కువగా
    0.46
    🕣
    0.45
     యొక్క
    0.45
    人不
    0.45
     உண்மையில்
    0.44
     오히려
    0.44
    ның
    0.43
    Activations Density 0.035%

    No Known Activations