© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86766
    Prev
    Next
    INDEX
    Explanations

    United States government entities

    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
     американ
    -0.88
     USA
    -0.88
     americana
    -0.83
    Uris
    -0.79
     amerik
    -0.76
     Contribu
    -0.75
    iiiii
    -0.74
    americano
    -0.73
    iiii
    -0.73
    satu
    -0.71
    POSITIVE LOGITS
    cellular
    1.11
     Chamber
    1.05
     Census
    0.99
     Patent
    0.87
     Constitution
    0.84
     Senator
    0.84
     Army
    0.82
    naux
    0.81
    坦克
    0.79
     Cellular
    0.79
    Activations Density 0.084%

    No Known Activations