© 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. 22-GEMMASCOPE-RES-131K
    4. 40355
    Prev
    Next
    INDEX
    Explanations

    time and dates

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

    The neuron fires on tokens containing digits or numeric data (dates, times, counts, IDs, etc.).

    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
    鱻
    -1.39
     considér
    -1.16
     funciones
    -1.14
     emocion
    -1.13
    烀
    -1.12
     carrinho
    -1.07
     contempla
    -1.07
    NESDAY
    -1.06
    泐
    -1.06
    歺
    -1.05
    POSITIVE LOGITS
     with
    1.32
     still
    1.05
     or
    1.03
     alongside
    1.03
     while
    1.02
     does
    1.02
     actually
    0.95
     in
    0.93
     as
    0.92
     despite
    0.92
    Activations Density 0.006%

    No Known Activations