© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67085
    Prev
    Next
    INDEX
    Explanations

    DOI and citation patterns

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

    The neuron activates on numeric tokens—years, page numbers, DOI segments, and other standalone 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
     they
    -1.15
    éfonos
    -1.05
    龱
    -1.02
     Tienen
    -1.01
     Sólo
    -0.99
    ärin
    -0.99
    Then
    -0.98
    ๔
    -0.97
     kazi
    -0.96
    ୈ
    -0.95
    POSITIVE LOGITS
     nonostante
    1.11
    軾
    1.08
    県の
    1.05
     osserva
    1.02
    」，
    1.02
    guarded
    1.01
     gesehen
    0.98
    ៍
    0.98
     chiese
    0.98
    aneity
    0.97
    Activations Density 0.002%

    No Known Activations