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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58464
    Prev
    Next
    INDEX
    Explanations

    numbered districts and parishes

    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
     транспор
    -0.84
    Dominic
    -0.84
     Dominic
    -0.84
    Dank
    -0.79
    тивных
    -0.77
    вление
    -0.75
    酚
    -0.71
    焄
    -0.71
     cana
    -0.70
    慢性
    -0.69
    POSITIVE LOGITS
     congressional
    1.70
     electoral
    1.69
     district
    1.54
     Congressional
    1.43
     districts
    1.39
     parliamentary
    1.34
     judicial
    1.31
     administrative
    1.28
     parish
    1.27
     Administrative
    1.24
    Activations Density 0.164%

    No Known Activations