© 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. 22-GEMMASCOPE-RES-131K
    7. 36463
    Prev
    Next
    INDEX
    Explanations

    periods and special occasions

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

    The neuron fires on numeric tokens—whole numbers, decimals, and percentages—in 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_22/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
    rador
    -1.13
    せっかく
    -1.06
    까지
    -0.97
    ultar
    -0.96
     Precio
    -0.96
    略歴
    -0.94
     ابتدا
    -0.93
     Xun
    -0.92
    त्व
    -0.92
     resultaten
    -0.91
    POSITIVE LOGITS
     during
    1.47
     when
    1.38
     winter
    1.34
     year
    1.30
     day
    1.30
     night
    1.23
     Christmas
    1.18
     summer
    1.17
     morning
    1.16
     December
    1.15
    Activations Density 0.083%

    No Known Activations