© 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. 66744
    Prev
    Next
    INDEX
    Explanations

    time-related updates and personal statements

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

    The neuron activates on standalone numeric tokens (e.g. scores, counts, or other isolated numbers).

    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
    几年
    -1.01
     if
    -1.01
    <eos>
    -0.99
    受欢迎
    -0.97
     исследование
    -0.96
    remarks
    -0.96
    BACKGROUND
    -0.96
    Remarks
    -0.94
     OG
    -0.93
     учре
    -0.93
    POSITIVE LOGITS
     today
    1.60
     updates
    1.38
     ativar
    1.34
     tonight
    1.32
     update
    1.22
     atualizar
    1.20
     again
    1.20
     tomorrow
    1.17
     yesterday
    1.15
     сегодня
    1.10
    Activations Density 0.012%

    No Known Activations