© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9617
    Prev
    Next
    INDEX
    Explanations

    dates in various languages

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

    The neuron fires on numbers used as day‐of‐month date markers (e.g. the numerals in “29 de noviembre” or “10 de diciembre”).

    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
    ↵↵↵
    -2.38
     
    -2.20
    to
    -2.17
    with
    -2.17
     has
    -2.11
     if
    -2.11
    the
    -2.03
    D
    -2.03
    H
    -1.98
    and
    -1.93
    POSITIVE LOGITS
     dieß
    2.25
    鹛
    2.23
     ſol
    2.14
    Doktor
    2.14
    
    1.96
    kadang
    1.96
    Wady
    1.89
     広場
    1.87
    луйста
    1.82
    蟊
    1.82
    Activations Density 0.001%

    No Known Activations