© 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. 34-GEMMASCOPE-RES-131K
    7. 90228
    Prev
    Next
    INDEX
    Explanations

    Iranian, Palestine, Students, progressive, democratic, national

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

    This neuron fires on document metadata and section headings (e.g. titles and header lines).

    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
    共产
    -0.80
    🕳
    -0.79
     menek
    -0.74
     sábado
    -0.74
     ۲۰۱
    -0.73
    premi
    -0.73
     året
    -0.72
    糜
    -0.71
    務省
    -0.71
     påvir
    -0.71
    POSITIVE LOGITS
     progressive
    1.54
    progressive
    1.27
     прогре
    1.15
     democratic
    1.14
     демокра
    1.07
     bourgeois
    1.06
     masses
    1.06
     nationalities
    1.03
     antif
    1.02
     PROGRESS
    0.97
    Activations Density 0.023%

    No Known Activations