© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7765
    Prev
    Next
    INDEX
    Explanations

    non-english or formal conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite

    end of sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ज्यादातर
    0.79
     żeby
    0.71
     Everybody
    0.70
    がたくさん
    0.70
    すごく
    0.68
     把
    0.68
     그다음에
    0.68
     කියලා
    0.68
     अगर
    0.65
    っていう
    0.65
    POSITIVE LOGITS
     alas
    1.01
    倘
    1.00
     aisément
    0.99
     हेतु
    0.98
     wherein
    0.95
     किंतु
    0.95
     iż
    0.95
     ибо
    0.91
    诸多
    0.90
     whilst
    0.87
    Activations Density 0.188%

    No Known Activations