© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3175
    Prev
    Next
    INDEX
    Explanations

    election and campaign discourse

    np_acts-logits-general · gemini-2.5-flash-lite

    political elections and parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aiguë
    0.55
     Enzym
    0.50
     enzim
    0.49
     enzym
    0.49
     sedent
    0.48
     enzyme
    0.47
     enzymes
    0.46
    ⛲
    0.46
     poissons
    0.46
     isothermal
    0.45
    POSITIVE LOGITS
     election
    1.97
    Election
    1.87
    election
    1.82
     electoral
    1.80
     Election
    1.79
     Democrats
    1.77
     voters
    1.74
     candidate
    1.73
    candidate
    1.73
     candidates
    1.73
    Activations Density 0.439%

    No Known Activations