© 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. 104620
    Prev
    Next
    INDEX
    Explanations

    political opposition leaders and parties

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

    This neuron responds to mentions of political parties and leadership titles (e.g. "Opposition," "Labor," "Prime Minister," "Opposition Leader").

    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
    qued
    -1.01
     Belajar
    -0.98
     ziyaretçi
    -0.94
    omite
    -0.93
    引言
    -0.93
     homicidio
    -0.92
    */
    -0.91
    getCmp
    -0.90
     betraying
    -0.90
    Integrating
    -0.88
    POSITIVE LOGITS
     opposition
    1.27
    stā
    0.98
     Opposition
    0.95
     funcionando
    0.93
    opposition
    0.90
     oposición
    0.90
     ponto
    0.88
     during
    0.88
     എ
    0.88
     press
    0.87
    Activations Density 0.052%

    No Known Activations