© 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. 34-GEMMASCOPE-RES-131K
    7. 115577
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    The neuron primarily detects day‐of‐week mentions (e.g. “Thursday,” “Saturday,” “Friday,” etc.) in date expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Thursday
    -1.42
     Wednesday
    -1.32
     Tuesday
    -1.30
     Saturday
    -1.23
     Monday
    -1.13
     Friday
    -1.13
    Thursday
    -1.09
    Saturday
    -1.05
     Sunday
    -0.95
    ...,
    -0.94
    POSITIVE LOGITS
     réjou
    1.08
     régal
    1.04
     verrou
    1.03
     relâche
    1.02
    ὧ
    1.00
     fidé
    0.98
     favoriser
    0.95
     révé
    0.94
     rempliss
    0.91
     douleurs
    0.91
    Activations Density 0.040%

    No Known Activations