© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30557
    Prev
    Next
    INDEX
    Explanations

    architectural design studios

    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
    岖
    -0.75
     giản
    -0.73
     risks
    -0.72
    ◥
    -0.72
    mcs
    -0.70
     LOCATIONS
    -0.69
    遅
    -0.68
     relazioni
    -0.67
     tráng
    -0.66
     dha
    -0.65
    POSITIVE LOGITS
     studio
    1.04
     studios
    0.99
     Studio
    0.93
     Architectural
    0.91
     Landscape
    0.86
     thesis
    0.84
    Studio
    0.81
     Preservation
    0.81
    Architectural
    0.79
    studio
    0.77
    Activations Density 0.021%

    No Known Activations