© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16104
    Prev
    Next
    INDEX
    Explanations

    lists of items to find

    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
    strMeal
    0.51
     нама
    0.50
    椏
    0.50
    ăpadă
    0.48
    āda
    0.48
    клад
    0.47
     magnetism
    0.46
    돈
    0.46
    槅
    0.46
     божомолдор
    0.46
    POSITIVE LOGITS
     Show
    0.47
     Pal
    0.45
     only
    0.43
     Success
    0.43
     Trail
    0.42
     只
    0.41
     Protect
    0.39
     App
    0.39
     سي
    0.39
     Store
    0.39
    Activations Density 0.007%

    No Known Activations