© 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. 34-GEMMASCOPE-RES-131K
    7. 59653
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    The neuron strongly activates on numeric tokens—years, dates, times, and other standalone 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_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
     June
    -2.08
    June
    -2.06
    May
    -1.76
     May
    -1.72
     june
    -1.60
     JUNE
    -1.55
    JUNE
    -1.53
    june
    -1.48
     July
    -1.29
     summer
    -1.27
    POSITIVE LOGITS
     March
    2.19
    March
    1.81
     April
    1.63
     MARCH
    1.53
     março
    1.47
     marzo
    1.45
    April
    1.42
     március
    1.40
    MARCH
    1.36
    march
    1.33
    Activations Density 0.087%

    No Known Activations