Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7801
    Prev
    Next
    INDEX
    Explanations

    ui related code

    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
    Duties
    -0.74
    nase
    -0.70
    ępu
    -0.69
    hase
    -0.69
     Lucio
    -0.67
     seguire
    -0.67
     Verk
    -0.67
    mitos
    -0.66
    Liberal
    -0.66
    Goed
    -0.66
    POSITIVE LOGITS
    ui
    3.86
     ui
    3.69
     UI
    2.83
    UI
    2.50
     Ui
    2.44
    Ui
    2.31
    UIS
    1.37
    uis
    1.31
     UIS
    1.28
    setupUi
    1.20
    Activations Density 0.044%

    No Known Activations