© 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. 34-GEMMASCOPE-RES-131K
    4. 84945
    Prev
    Next
    INDEX
    Explanations

    this week, this year, this month

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

    The neuron is detecting numeric tokens (e.g. years, counts, or 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_34/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
     this
    -2.17
     today
    -1.89
     nowadays
    -1.43
     tonight
    -1.41
    aujourd
    -1.34
     oggi
    -1.32
     yesterday
    -1.27
     last
    -1.27
     heute
    -1.19
     lately
    -1.18
    POSITIVE LOGITS
     onwards
    1.07
    ш
    1.02
     virtuales
    1.01
     Strahl
    1.00
     If
    0.98
    中でも
    0.95
     temprano
    0.95
    quiler
    0.93
     procedentes
    0.93
    таки
    0.92
    Activations Density 0.028%

    No Known Activations