© 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. 75473
    Prev
    Next
    INDEX
    Explanations

    number and age range

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

    The neuron selectively activates on numeric tokens (counts, measurements, years, percentages) 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
     between
    -1.14
    }<
    -1.10
     below
    -0.98
     less
    -0.94
     بین
    -0.91
     Between
    -0.89
     между
    -0.88
     under
    -0.84
     $<
    -0.84
     zwischen
    -0.84
    POSITIVE LOGITS
     старше
    1.85
     above
    1.71
    Above
    1.59
     age
    1.55
     older
    1.52
     mayores
    1.51
     acima
    1.45
     بالای
    1.41
     aged
    1.40
     over
    1.35
    Activations Density 0.076%

    No Known Activations