© 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. 81053
    Prev
    Next
    INDEX
    Explanations

    proper nouns and diverse scripts

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

    This neuron detects tokens that are part of proper nouns or other capitalized named entities (including names, titles, and numeric identifiers).

    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
     commutative
    -0.85
    reef
    -0.77
     sorts
    -0.72
     INFO
    -0.71
     ISSN
    -0.71
    chic
    -0.68
    失踪
    -0.68
    视着
    -0.68
    enrich
    -0.68
    ète
    -0.68
    POSITIVE LOGITS
     Menlo
    0.77
     PIB
    0.77
     muta
    0.77
     примі
    0.76
     Carb
    0.76
    ἷ
    0.75
    蜉
    0.74
     изме
    0.73
    構築
    0.72
     lgbt
    0.72
    Activations Density 0.059%

    No Known Activations