© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45212
    Prev
    Next
    INDEX
    Explanations

    start, quarter, half, comeback

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

    The neuron strongly activates on references to numbered or ordered segments and metrics—especially sports/game time units (halves, quarters, periods), ordinal markers (first, second, third), and other numeric/statistical indicators.

    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
    日発売
    -1.35
     кілька
    -1.27
     bezeichnen
    -1.14
     proste
    -1.13
     sumamente
    -1.07
     σας
    -1.06
     усі
    -1.05
     ТАК
    -1.05
     осуществляется
    -1.03
     schlug
    -1.03
    POSITIVE LOGITS
    齶
    1.24
    鲼
    1.23
     ?>
    
    1.17
    мала
    1.15
    šti
    1.15
    логу
    1.14
    IAI
    1.14
    чя
    1.13
     crocs
    1.12
    фаль
    1.12
    Activations Density 0.032%

    No Known Activations