© 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. 10-GEMMASCOPE-RES-131K
    4. 47600
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    The neuron spotlights temporal schedule information—especially day‐of‐week names, dates, and numeric time or duration tokens.

    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
     هاي
    -1.34
    ਲ਼
    -1.29
    layoutParams
    -1.25
    caj
    -1.25
    hodné
    -1.24
    снимок
    -1.24
     resten
    -1.23
    UnifiedTopology
    -1.23
     amie
    -1.23
     helse
    -1.23
    POSITIVE LOGITS
     また
    1.26
    ヒント
    1.22
     według
    1.22
    できれば
    1.21
     cause
    1.13
    深い
    1.12
    一支
    1.10
    深く
    1.08
     A
    1.06
    escola
    1.06
    Activations Density 0.066%

    No Known Activations