© 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. 4620
    Prev
    Next
    INDEX
    Explanations

    holidays and celebrations

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

    signals intelligence, start screen, c++, natural language, artificial intelligence, haiku

    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
     Emeritus
    0.54
     Jego
    0.46
     Coordin
    0.44
     Komitet
    0.42
     “(
    0.40
     Serikat
    0.39
     Confeder
    0.38
     “[
    0.38
         
    0.38
    \"{
    0.38
    POSITIVE LOGITS
     california
    0.55
     england
    0.54
    cellaneous
    0.49
    adaşlar
    0.48
     africa
    0.47
     indonesia
    0.45
     october
    0.45
     andolan
    0.45
     barcelona
    0.44
    etheless
    0.43
    Activations Density 0.785%

    No Known Activations