© 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. 34-GEMMASCOPE-RES-131K
    7. 91380
    Prev
    Next
    INDEX
    Explanations

    legal and scientific citations

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

    This neuron detects the numeric components of legal and academic citations—especially the volume, year, and page 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
     after
    -1.00
     one
    -0.78
     Going
    -0.71
     Sensitive
    -0.69
    bedaan
    -0.69
    Negro
    -0.69
    Sensitive
    -0.68
    鹦
    -0.68
     Lovell
    -0.67
     Group
    -0.67
    POSITIVE LOGITS
     AppCompatTheme
    0.83
     αυτά
    0.82
     EXCLUS
    0.77
     forgets
    0.75
    separator
    0.75
    meli
    0.73
    쏴
    0.72
    原则
    0.72
    (!$
    0.71
     abit
    0.71
    Activations Density 0.033%

    No Known Activations