© 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. 11961
    Prev
    Next
    INDEX
    Explanations

    empire and ecosystem

    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
     ឬ
    0.54
     zodat
    0.52
     seguinte
    0.51
     ވަ
    0.50
    setHeader
    0.50
     atthakath
    0.50
    𒁕
    0.50
     வழங்கப்படும்
    0.49
     كانت
    0.49
    amboat
    0.48
    POSITIVE LOGITS
     system
    0.63
     expansion
    0.62
     empire
    0.60
    0
    0.57
    CH
    0.55
     network
    0.54
    システム
    0.52
    )
    0.51
    ’
    0.51
     expansions
    0.50
    Activations Density 0.069%

    No Known Activations