© 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. 41579
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    The neuron activates on numeric tokens—years, dates, measurements, and other numbers—in the text.

    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
    .”
    -1.79
     if
    -1.66
     such
    -1.60
     primeras
    -1.47
     as
    -1.45
    OREM
    -1.37
     propias
    -1.37
    cuatro
    -1.34
    )$;
    -1.34
    。
    -1.31
    POSITIVE LOGITS
     was
    1.69
    目光
    1.66
    ATUS
    1.48
    niająca
    1.47
     guma
    1.45
    UMENTO
    1.45
    ième
    1.45
    不动
    1.43
     next
    1.41
    かもし
    1.41
    Activations Density 0.259%

    No Known Activations