© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1352
    Prev
    Next
    INDEX
    Explanations

    operating systems and binaries

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

    operating system names

    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
     atletas
    0.51
    細胞
    0.47
     細胞
    0.46
     atleta
    0.46
     sphinct
    0.45
     obstetric
    0.45
     outfield
    0.45
    駝
    0.45
    看護
    0.45
     bracelets
    0.45
    POSITIVE LOGITS
     Windows
    2.41
    Windows
    2.33
     Linux
    2.06
    Linux
    1.95
     linux
    1.86
     MacOS
    1.83
     Ubuntu
    1.74
    windows
    1.73
    WINDOWS
    1.73
     OSX
    1.69
    Activations Density 0.717%

    No Known Activations