© 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. 33337
    Prev
    Next
    INDEX
    Explanations

    council, mayor, district, election

    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
     sects
    -0.75
     site
    -0.73
     Minion
    -0.70
    nitts
    -0.70
    更是
    -0.69
     Site
    -0.69
     Secretary
    -0.69
     tissues
    -0.68
     government
    -0.68
     numerous
    -0.68
    POSITIVE LOGITS
    tagHelperRunner
    0.87
     councillor
    0.84
     councillors
    0.83
    council
    0.83
    Fluor
    0.82
    ]:
    0.79
    Mayor
    0.78
     ecológica
    0.77
     lateinit
    0.76
     cidade
    0.74
    Activations Density 0.012%

    No Known Activations