© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10191
    Prev
    Next
    INDEX
    Explanations

    socket and socks

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

    server real-time updates

    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
     जाय
    0.43
     हेल
    0.42
    SAR
    0.40
     কমল
    0.39
     plast
    0.39
    木の
    0.38
    杞
    0.38
    刳
    0.38
    楷
    0.38
    ophenyl
    0.37
    POSITIVE LOGITS
     socket
    2.13
     Socket
    2.03
     sockets
    1.98
     websocket
    1.95
     WebSocket
    1.95
    socket
    1.91
    Socket
    1.88
     sok
    1.86
     SOCKET
    1.82
    sockets
    1.81
    Activations Density 0.048%

    No Known Activations