© 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. 34-GEMMASCOPE-RES-131K
    7. 93236
    Prev
    Next
    INDEX
    Explanations

    time periods like weeks

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

    This neuron detects temporal quantitative expressions—numbers or quantifiers paired with time units or durations (e.g. “almost a week,” “two weeks,” “entering its 12th day,” “now,” percentages of containment, etc.).

    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
    明年
    -1.21
    来年
    -1.18
     Years
    -1.11
    YEAR
    -1.10
    Years
    -1.09
     années
    -1.09
    Year
    -1.07
    四季
    -1.04
     الساعة
    -1.00
     בשנת
    -0.99
    POSITIVE LOGITS
     weeks
    5.50
     week
    5.25
     month
    3.95
    week
    3.59
     Weeks
    3.58
    weeks
    3.58
     semanas
    3.50
    Weeks
    3.48
     Week
    3.22
    Week
    3.13
    Activations Density 0.201%

    No Known Activations