© 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. 103730
    Prev
    Next
    INDEX
    Explanations

    events on dates

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

    The neuron detects numeric metadata—particularly years, dates, and other numeric tokens associated with events (e.g., premieres, releases, season 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
     kuulu
    -1.29
    Ẹ
    -1.23
     voidaan
    -1.16
    ViewChild
    -1.13
     handleMessage
    -1.13
     olivat
    -1.12
     löyty
    -1.10
    ONS
    -1.10
    avigation
    -1.10
    ustomed
    -1.09
    POSITIVE LOGITS
     on
    8.50
     On
    2.81
    On
    2.69
     στις
    2.03
     على
    1.93
     ביום
    1.92
    Pada
    1.91
    on
    1.84
     pada
    1.78
     на
    1.72
    Activations Density 0.444%

    No Known Activations