© 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. 69179
    Prev
    Next
    INDEX
    Explanations

    human history and time

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

    The neuron strongly activates on words that set a historical or chronological frame (e.g. “history,” “recorded,” “throughout,” “since,” “beginning”), so it’s detecting references to time spans or historical context.

    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
    -1.39
    ִּ
    -1.34
    ַּ
    -1.34
    וּ
    -1.26
     new
    -1.26
     electronics
    -1.26
     email
    -1.19
     you
    -1.17
    corer
    -1.13
     online
    -1.12
    POSITIVE LOGITS
     centuries
    1.33
     EXAMPLES
    1.24
     generations
    1.16
     різ
    1.15
     chré
    1.15
    quité
    1.14
    inspiring
    1.13
    Exemples
    1.13
     religieux
    1.13
     Examples
    1.13
    Activations Density 0.094%

    No Known Activations