© 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. 25897
    Prev
    Next
    INDEX
    Explanations

    character roles and relationships

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

    The neuron strongly activates on words that denote people’s demographic or identity attributes (e.g. race, gender, sexual orientation, disability).

    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
    當時
    -1.16
    誰か
    -1.04
     seseorang
    -1.04
    嚐
    -1.02
    於是
    -0.98
    掙
    -0.97
    樣子
    -0.94
     fisico
    -0.94
     morons
    -0.93
    オム
    -0.92
    POSITIVE LOGITS
     protective
    1.23
     gay
    1.23
     ner
    1.15
     alcoholic
    1.12
    African
    1.09
     sche
    1.06
     African
    1.04
     drug
    1.03
     loud
    1.02
     Buddhist
    1.02
    Activations Density 0.045%

    No Known Activations