© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39244
    Prev
    Next
    INDEX
    Explanations

    month day, year

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

    The neuron activates on date expressions (month names and numeric day/year 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_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
    や
    -1.17
    Circles
    -1.09
    zęd
    -1.09
    ご注文
    -1.07
     universitaria
    -1.06
    Hermoso
    -1.06
     also
    -1.05
     furthermore
    -1.03
    除此之外
    -1.02
     barrage
    -1.02
    POSITIVE LOGITS
    corrhi
    1.06
     on
    1.01
    ৳
    0.97
    imageio
    0.93
     antiguas
    0.92
    водом
    0.92
    вере
    0.91
    🧾
    0.91
    uring
    0.91
    uration
    0.90
    Activations Density 0.064%

    No Known Activations