© 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. 6934
    Prev
    Next
    INDEX
    Explanations

    at the beginning

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

    The neuron detects references to something occurring at the start (or beginning) of an event, period, or location.

    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
     заканчи
    -1.12
    下一步
    -0.90
     endDate
    -0.87
    を経て
    -0.85
     finishes
    -0.84
    EndDate
    -0.81
    endDate
    -0.81
    ɵɵelementEnd
    -0.78
    Finish
    -0.77
    最后一个
    -0.76
    POSITIVE LOGITS
     beginning
    4.84
     начале
    3.70
    beginning
    3.66
    Beginning
    3.28
     Beginning
    3.19
     начала
    3.11
     Beginn
    3.09
     начало
    3.06
     beginnings
    3.03
     początku
    2.95
    Activations Density 0.093%

    No Known Activations