© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11156
    Prev
    Next
    INDEX
    Explanations

    component or parking

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

    route definitions, component declarations

    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_40_width_16k_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
    路径
    0.53
     path
    0.51
     путь
    0.49
     pathway
    0.47
     basePath
    0.47
     경로
    0.46
    ルート
    0.46
    ('/:
    0.44
    ArchivePath
    0.42
    ("/
    0.41
    POSITIVE LOGITS
     component
    0.45
    component
    0.43
     компонен
    0.43
    components
    0.42
     Kerry
    0.41
     components
    0.40
     bo
    0.38
     ফ্র
    0.38
    元件
    0.38
     Ker
    0.38
    Activations Density 0.000%

    No Known Activations