© 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. 67962
    Prev
    Next
    INDEX
    Explanations

    cultural diversity and social issues

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

    This neuron fires on title‐style or heading phrases that present educational or resource offerings (e.g. “in the Classroom with these Resources”).

    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
     for
    -1.60
    "});
    -1.37
     alvor
    -1.30
     after
    -1.28
     måneder
    -1.27
    猡
    -1.27
     selepas
    -1.23
    Quels
    -1.19
     could
    -1.18
    奬
    -1.18
    POSITIVE LOGITS
     our
    1.50
     可愛い
    1.42
     acciones
    1.42
     السياس
    1.23
    พูด
    1.16
     zabur
    1.15
     разных
    1.15
     öff
    1.13
    jsii
    1.13
     mejoras
    1.13
    Activations Density 0.014%

    No Known Activations