© 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. 109543
    Prev
    Next
    INDEX
    Explanations

    national council websites

    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
     talking
    -0.76
     internationally
    -0.75
     نوف
    -0.70
     Literary
    -0.70
     grammar
    -0.70
    臥
    -0.68
     ASSOCI
    -0.66
     alivio
    -0.66
    лье
    -0.65
    postId
    -0.64
    POSITIVE LOGITS
    astet
    0.77
    Raum
    0.66
    即使
    0.65
    Cynthia
    0.65
    currentTime
    0.65
    idig
    0.64
     súng
    0.64
    RAL
    0.64
     çerçe
    0.63
    irci
    0.63
    Activations Density 0.035%

    No Known Activations