© 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. 84387
    Prev
    Next
    INDEX
    Explanations

    presidential elections and campaigns

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

    The neuron strongly activates on mentions of political candidates’ names (e.g. “Bernie Sanders,” “Hillary Clinton,” “Mitt Romney,” “Barack Obama”) and related election‐context terms.

    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
     at
    -1.17
    XCTAssertEqual
    -1.10
     primeiras
    -1.09
     Estos
    -1.09
     Petitioners
    -1.09
    ヮ
    -1.09
     Ahora
    -1.08
     mesmas
    -1.06
    arreg
    -1.05
     Penalties
    -1.04
    POSITIVE LOGITS
     America
    1.26
     бампер
    1.23
     President
    1.22
    useNewUrlParser
    1.22
    ние
    1.21
    スポンサーリンク
    1.19
    にほんブログ村
    1.17
     птицы
    1.16
     bambu
    1.15
    さてさて
    1.13
    Activations Density 0.080%

    No Known Activations