© 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. 36350
    Prev
    Next
    INDEX
    Explanations

    child play and entertainment

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

    The neuron fires on upbeat, promotional adjectives describing children’s toys (e.g. “fun,” “educational,” “creative,” “durable”).

    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
    ּוֹ
    -1.93
    ִּ
    -1.78
    ֶּ
    -1.41
    ַּ
    -1.32
    ־ה
    -1.29
     in
    -1.24
    ְּ
    -1.23
     повышение
    -1.18
     public
    -1.15
    ְר
    -1.15
    POSITIVE LOGITS
    ׇ
    1.54
     chré
    1.44
     τὴν
    1.38
     religieux
    1.37
     play
    1.34
     τὸν
    1.34
     botanique
    1.34
     cukru
    1.34
     religieuses
    1.29
    heitsbild
    1.28
    Activations Density 0.044%

    No Known Activations