© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110541
    Prev
    Next
    INDEX
    Explanations

    end date/time

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

    This neuron detects mentions of “end” (e.g. end, End, END, enddate, End Time) indicating an ending time or range field.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    か
    -1.25
     =
    -1.16
    .*;
    -1.09
     fusca
    -1.06
     Լ
    -1.00
    <h2>
    -1.00
     rye
    -0.99
    ⵜ
    -0.98
     lacking
    -0.98
     is
    -0.97
    POSITIVE LOGITS
     sicher
    1.21
     endTime
    1.13
     promesa
    1.11
    իա
    1.09
     précise
    1.09
     镇
    1.09
    ,{\
    1.06
     táctil
    1.05
    Награ
    1.05
     에서
    1.05
    Activations Density 0.033%

    No Known Activations