© 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. 34-GEMMASCOPE-RES-131K
    7. 93964
    Prev
    Next
    INDEX
    Explanations

    in the age of

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

    The neuron activates on numeric tokens (e.g. years, percentages, 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
    そこ
    -0.98
     детства
    -0.92
    řeba
    -0.91
     внутренних
    -0.89
    iedler
    -0.88
     it
    -0.86
     majú
    -0.85
    habited
    -0.83
     Classic
    -0.82
    MQ
    -0.81
    POSITIVE LOGITS
     today
    2.77
     this
    2.19
     a
    2.05
     todays
    1.97
     times
    1.87
     era
    1.86
     aujourd
    1.85
     these
    1.84
     heutigen
    1.76
     сегодня
    1.71
    Activations Density 0.047%

    No Known Activations