© 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. 22-GEMMASCOPE-RES-131K
    4. 79801
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    The neuron fires on numeric tokens that are part of date or time references (e.g. years, day‐of‐month numbers).

    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
     remember
    -1.09
     коэффици
    -0.99
     財布
    -0.99
    коль
    -0.98
     они
    -0.96
     кли
    -0.94
     like
    -0.93
    тна
    -0.92
     MONTH
    -0.91
     подключения
    -0.91
    POSITIVE LOGITS
     間取り
    0.96
     والتي
    0.91
    と思ったら
    0.91
    Grap
    0.90
    難易
    0.89
    ancienne
    0.89
    Гар
    0.88
     previous
    0.87
    そうです
    0.85
    があるので
    0.85
    Activations Density 0.009%

    No Known Activations