© 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. 33264
    Prev
    Next
    INDEX
    Explanations

    plumbing and water systems

    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
    али
    -0.69
    MSC
    -0.68
     McFarland
    -0.68
     الدين
    -0.67
    규
    -0.67
    MEET
    -0.65
    ГУ
    -0.64
     ashtray
    -0.63
     pogo
    -0.63
     Riche
    -0.63
    POSITIVE LOGITS
     pipes
    3.09
     pipe
    2.78
     Pipes
    2.38
     Pipe
    2.28
    Pipe
    2.23
    pipes
    2.23
    pipe
    2.22
    Pipes
    2.14
     water
    1.92
     burst
    1.76
    Activations Density 0.015%

    No Known Activations