© 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. 77727
    Prev
    Next
    INDEX
    Explanations

    building structures

    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
     arrogance
    -0.85
     lighten
    -0.77
     Somali
    -0.77
     wickedness
    -0.76
    Basin
    -0.75
    Stal
    -0.74
    tida
    -0.73
    惬
    -0.71
     depression
    -0.71
     जल
    -0.71
    POSITIVE LOGITS
    build
    0.96
     build
    0.89
     BUILD
    0.86
     Build
    0.83
     Builds
    0.80
    构建
    0.73
     dipas
    0.73
     aho
    0.73
    lamos
    0.72
    viated
    0.69
    Activations Density 0.031%

    No Known Activations