© 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. 10-GEMMASCOPE-RES-131K
    7. 11487
    Prev
    Next
    INDEX
    Explanations

    recurring time periods

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

    The neuron detects recurring time‐period expressions introduced by “Each” (e.g. “Each day,” “Each year,” “Each week,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    　↓
    -1.75
    !”
    -1.70
     ausgesprochen
    -1.66
    Surprisingly
    -1.65
    ”、“
    -1.64
     inmiddels
    -1.63
    ,”
    -1.63
     Иванович
    -1.59
     預
    -1.59
    ・・・・・
    -1.59
    POSITIVE LOGITS
    烀
    1.89
     \
    1.88
     tetapi
    1.76
     jovem
    1.74
     \"
    1.70
    </th>
    1.69
    ↑↑↑</
    1.69
    蛱
    1.66
     mangiare
    1.66
     unſ
    1.66
    Activations Density 0.010%

    No Known Activations