© 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. 93739
    Prev
    Next
    INDEX
    Explanations

    eternity, perpetuity, forever, centuries, posterity

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

    The neuron activates strongly on numeric tokens (years, counts, code indices, etc.), i.e. it detects 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_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
     Elves
    -0.77
     Garth
    -0.70
     europa
    -0.70
    kriv
    -0.69
     Vargas
    -0.69
    cena
    -0.69
     DW
    -0.69
     endpoint
    -0.68
    Elle
    -0.68
    aS
    -0.67
    POSITIVE LOGITS
     eternity
    5.22
     Eternity
    3.83
    etern
    3.39
    Etern
    3.08
     etern
    2.73
     perpetuity
    2.67
     eternal
    2.50
     Etern
    2.03
     eternally
    2.00
     eter
    1.98
    Activations Density 0.040%

    No Known Activations