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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7859
    Prev
    Next
    INDEX
    Explanations

    US senators and politicians

    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
     Corbyn
    -1.04
    Facebook
    -0.98
     née
    -0.97
    testng
    -0.94
    DRAG
    -0.93
    RNN
    -0.92
     Sunak
    -0.92
    ίη
    -0.91
    𓂂
    -0.91
     Facebook
    -0.90
    POSITIVE LOGITS
     Duk
    1.09
     Dole
    0.93
     Senator
    0.91
     Bork
    0.87
     Quay
    0.87
     Gep
    0.86
     Gore
    0.84
     Bush
    0.83
    Skład
    0.83
    ष्य
    0.82
    Activations Density 0.077%

    No Known Activations