© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91737
    Prev
    Next
    INDEX
    Explanations

    democratic presidential campaigns

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

    The neuron fires on mentions of political context—party labels, candidate names, and election years.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Altre
    -0.76
    NamedQueries
    -0.75
    BIA
    -0.75
    쌈
    -0.74
    ielt
    -0.72
     progresso
    -0.71
     dismin
    -0.70
    бовь
    -0.69
     華
    -0.67
    grunge
    -0.67
    POSITIVE LOGITS
     presidential
    3.33
     Presidential
    2.69
    Presidential
    2.11
     президент
    1.75
     presidencial
    1.64
     PRESIDENT
    1.61
     president
    1.51
     primary
    1.45
    总统
    1.41
     présidentielle
    1.41
    Activations Density 0.061%

    No Known Activations