© 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. 30277
    Prev
    Next
    INDEX
    Explanations

    creating or defining UI elements

    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
    راتيج
    -0.87
    oxyd
    -0.75
     Bedrooms
    -0.75
    揾
    -0.73
     Xin
    -0.73
     tanah
    -0.72
     będę
    -0.69
     ympä
    -0.69
     fuertemente
    -0.68
     Bünd
    -0.68
    POSITIVE LOGITS
     build
    1.97
    build
    1.63
    Build
    1.33
     built
    1.26
     builds
    1.24
     Build
    1.16
    BUILD
    1.09
    builder
    1.08
     BUILD
    1.07
     building
    1.06
    Activations Density 0.001%

    No Known Activations