© 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. 47790
    Prev
    Next
    INDEX
    Explanations

    announcements and investigation

    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
    opilot
    0.45
    俠
    0.44
     estudantes
    0.44
     harn
    0.44
    statistik
    0.43
     Nikhil
    0.43
     toa
    0.43
    נים
    0.43
     reformer
    0.43
     INDIAN
    0.42
    POSITIVE LOGITS
    ม
    0.48
    پ
    0.47
     তারা
    0.44
    ׃
    0.44
    ни
    0.43
     ต้อง
    0.42
    ور
    0.42
    л
    0.42
    دی
    0.41
     decidedly
    0.40
    Activations Density 0.006%

    No Known Activations