© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63237
    Prev
    Next
    INDEX
    Explanations

    historical figures and eras

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

    The neuron is activated by numeric tokens—especially years, dates, and number ranges.

    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
     Trieste
    -0.92
     ۱۹
    -0.90
     ALFRED
    -0.85
     американ
    -0.85
    Nationalité
    -0.84
    先代
    -0.84
     metron
    -0.84
     Vichy
    -0.84
     applau
    -0.84
     sphinx
    -0.84
    POSITIVE LOGITS
     seventeenth
    1.73
     Elizabethan
    1.61
     sixteenth
    1.59
     Renaissance
    1.59
     Reformation
    1.41
    Renaissance
    1.41
     XVI
    1.34
     XVII
    1.27
     Tudor
    1.16
     medieval
    1.12
    Activations Density 0.277%

    No Known Activations