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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40546
    Prev
    Next
    INDEX
    Explanations

    diffusion, gingerbread, crossing, polynomial, combine

    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
    幸福
    0.42
     అతను
    0.42
    ان
    0.40
    很简单
    0.40
     geeign
    0.40
     ofx
    0.39
    兇
    0.39
    只要
    0.38
    相结合
    0.38
    addPreferred
    0.38
    POSITIVE LOGITS
    rollers
    0.49
     ORIGINAL
    0.45
     wrestled
    0.45
    dU
    0.44
     الاعدادي
    0.43
    %.
    0.43
    %).
    0.42
    ၀
    0.42
     intellectually
    0.42
    zinger
    0.41
    Activations Density 0.042%

    No Known Activations