© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11092
    Prev
    Next
    INDEX
    Explanations

    political party nominations and primaries

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

    The neuron strongly activates on mentions of political party names or related party/nomination terms (e.g. “PDP,” “Republican,” “nomination,” “primary”).

    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
     Initializes
    -1.13
    わからない
    -1.11
    addCriterion
    -1.02
    わから
    -1.02
    ところです
    -1.00
     '
    -1.00
    Cuando
    -0.99
    ₵
    -0.98
    Try
    -0.98
    分からない
    -0.98
    POSITIVE LOGITS
    によって
    1.06
    での
    1.03
     desean
    0.97
     Autorin
    0.97
    emporio
    0.97
    enangan
    0.96
    efined
    0.95
     loyalty
    0.95
    Elek
    0.94
    ması
    0.93
    Activations Density 0.027%

    No Known Activations