© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3187
    Prev
    Next
    INDEX
    Explanations

    conjunctions and continuation

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

    combination and listing

    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
     maupun
    1.09
    及
    0.91
     તેમજ
    0.80
    以及
    0.79
     sowie
    0.76
    および
    0.75
     lẫn
    0.74
    및
    0.73
     sekä
    0.72
     एवं
    0.71
    POSITIVE LOGITS
     并
    1.34
    并在
    1.30
    并将
    1.30
    并
    1.27
     並
    1.20
    並
    1.20
    並且
    1.18
    并且
    1.08
    하고
    1.02
    并通过
    1.02
    Activations Density 1.238%

    No Known Activations