© 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. 17696
    Prev
    Next
    INDEX
    Explanations

    explaining or attempting something

    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
     ot
    0.34
     ((
    0.31
     subcontractor
    0.30
     {
    0.30
     tableware
    0.30
     Lopez
    0.29
     won
    0.29
     sinon
    0.29
     modificare
    0.29
     να
    0.29
    POSITIVE LOGITS
    便于
    0.41
    杲
    0.37
    æn
    0.37
    凡
    0.36
    便捷
    0.35
     நடைபெற்ற
    0.35
    ಗರ
    0.35
    简洁
    0.35
     eloquently
    0.35
    ！！！
    0.34
    Activations Density 0.036%

    No Known Activations