© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82645
    Prev
    Next
    INDEX
    Explanations

    certified mail, precise measurement, TCP window

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     modelAndView
    -0.84
    INDER
    -0.71
    ヒット
    -0.71
    Pont
    -0.69
    diert
    -0.68
     kjø
    -0.68
     Jof
    -0.67
    Scholar
    -0.66
     sicurezza
    -0.65
    yoti
    -0.64
    POSITIVE LOGITS
     window
    1.55
     Window
    1.31
    window
    1.18
    Window
    1.18
     receiver
    1.14
     WINDOW
    1.11
    ACK
    1.02
    WindowSize
    1.02
     sliding
    1.02
    WINDOW
    0.99
    Activations Density 0.018%

    No Known Activations