© 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. 2527
    Prev
    Next
    INDEX
    Explanations

    political party names

    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
    ける
    -0.78
    Glo
    -0.73
    Flex
    -0.71
     ziren
    -0.70
     keiner
    -0.70
    Green
    -0.69
     наз
    -0.69
    近くに
    -0.67
    延長
    -0.67
    pig
    -0.67
    POSITIVE LOGITS
     unit
    1.08
     workers
    0.95
     BJP
    0.90
     party
    0.84
    チョウ
    0.78
     Organizational
    0.77
     units
    0.77
    workers
    0.75
     scape
    0.75
     genotyping
    0.74
    Activations Density 0.012%

    No Known Activations