© 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. 22-GEMMASCOPE-RES-131K
    7. 75145
    Prev
    Next
    INDEX
    Explanations

    political candidates and elections

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

    The neuron fires strongly on the names of prominent political figures (especially presidential candidates).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.73
    Its
    -1.18
     their
    -1.17
     Italij
    -1.14
     Ortsteil
    -1.03
    niños
    -1.02
    Zubereitung
    -1.02
    Ձ
    -1.01
     durab
    -1.01
     especially
    -1.00
    POSITIVE LOGITS
     candidate
    1.28
     candidacy
    1.20
    )}}{
    1.16
     opponent
    1.15
     candidates
    1.12
     resultaat
    1.04
     potenciales
    1.03
     kateg
    1.03
     himself
    1.02
    %;">
    1.02
    Activations Density 0.050%

    No Known Activations