© 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. 11747
    Prev
    Next
    INDEX
    Explanations

    use files or articles

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

    web server setup and routes

    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
    raphic
    0.42
    (()
    0.41
    mongoose
    0.41
    mapping
    0.41
    搁
    0.38
    argument
    0.38
    MONG
    0.38
    物に
    0.38
     (){
    0.37
    lot
    0.37
    POSITIVE LOGITS
    ekyll
    0.42
     nale
    0.42
     '/',
    0.40
     '.',
    0.40
     menjawab
    0.39
     transient
    0.38
    (:,
    0.38
     face
    0.37
    的标准
    0.37
    标准
    0.37
    Activations Density 0.001%

    No Known Activations