© 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. 93101
    Prev
    Next
    INDEX
    Explanations

    dates and events

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

    This neuron detects date/time expressions, especially the word “on” and adjacent day or month names.

    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
     Sept
    -1.23
     June
    -1.23
     fifteenth
    -1.22
     Feb
    -1.21
     July
    -1.20
     Oct
    -1.20
     sixteenth
    -1.18
     September
    -1.17
     October
    -1.13
     April
    -1.12
    POSITIVE LOGITS
    ïne
    0.85
    μι
    0.79
     preis
    0.77
    imédia
    0.77
    睫
    0.76
    toHaveBeen
    0.75
     Vishnu
    0.73
     يمكن
    0.73
     VIDEOTAPE
    0.73
     olvas
    0.73
    Activations Density 0.116%

    No Known Activations