© 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. 84158
    Prev
    Next
    INDEX
    Explanations

    Democrats control seats

    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
     znan
    -0.87
    θεί
    -0.84
     cuarzo
    -0.83
    zieży
    -0.82
    zoeken
    -0.82
     autory
    -0.80
     печени
    -0.80
    Viited
    -0.79
     actualización
    -0.79
     oficiales
    -0.79
    POSITIVE LOGITS
     control
    1.77
    CONTROL
    1.46
    control
    1.46
     CONTROL
    1.45
     Control
    1.45
     seats
    1.31
    controlled
    1.30
    Control
    1.29
     flipped
    1.23
    Controlled
    1.22
    Activations Density 0.044%

    No Known Activations