© 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. 10-GEMMASCOPE-RES-131K
    7. 75430
    Prev
    Next
    INDEX
    Explanations

    quantified periods of time

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

    This neuron activates on numeric tokens, essentially identifying number values 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
    ↵↵
    -1.88
    -1.85
    但她
    -1.59
     when
    -1.55
     tomando
    -1.49
     wen
    -1.39
     gdy
    -1.39
    但却
    -1.38
     ...
    -1.37
     times
    -1.37
    POSITIVE LOGITS
     pantolon
    1.47
    ꨄ
    1.47
    ayaquil
    1.45
     elbise
    1.38
    Either
    1.37
    kuwa
    1.37
     хорошая
    1.35
    ÃO
    1.34
    izielle
    1.34
     detayl
    1.30
    Activations Density 0.021%

    No Known Activations