© 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. 91844
    Prev
    Next
    INDEX
    Explanations

    building features and amenities

    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
    centralwidget
    -0.91
     morti
    -0.85
     personale
    -0.84
     Databases
    -0.84
    unuh
    -0.83
    ۩
    -0.82
     Noël
    -0.82
     colonie
    -0.82
     estates
    -0.81
     vnode
    -0.81
    POSITIVE LOGITS
     retail
    1.13
     rooftop
    0.96
     bike
    0.95
     common
    0.93
     bicycle
    0.93
    Retail
    0.92
    LE
    0.91
    common
    0.91
     Common
    0.90
     lobby
    0.89
    Activations Density 0.020%

    No Known Activations