© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3702
    Prev
    Next
    INDEX
    Explanations

    superior performance

    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_40_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
     snugly
    0.43
     bhikkhave
    0.42
     příjem
    0.42
     እንቅ
    0.42
     clamped
    0.42
    বিধি
    0.40
    寤
    0.40
    লন
    0.40
    帏
    0.39
    uição
    0.39
    POSITIVE LOGITS
     superiority
    1.23
     performance
    1.20
     superior
    1.13
     성능
    1.12
    性能
    1.10
    superior
    1.08
     capabilities
    1.07
    Performance
    1.07
    performance
    1.06
     superiore
    0.99
    Activations Density 0.646%

    No Known Activations