© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117078
    Prev
    Next
    INDEX
    Explanations

    win or loss

    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
     something
    -1.07
    了一会儿
    -1.05
    在
    -1.02
    Var
    -1.00
     juntamente
    -0.96
    天氣
    -0.95
    の準備
    -0.94
     imó
    -0.93
    きょう
    -0.93
     hefty
    -0.93
    POSITIVE LOGITS
     in
    1.08
    
    0.96
    tų
    0.96
    撐
    0.95
    ษา
    0.94
    Sylvie
    0.93
    Capitol
    0.93
     displacements
    0.93
    iranje
    0.93
     என்ற
    0.91
    Activations Density 0.023%

    No Known Activations