© 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. 23908
    Prev
    Next
    INDEX
    Explanations

    authors, creators, or multiple items

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

    This neuron specializes in spotting numeric tokens—especially the year, volume, page, and other number fields common in reference and citation entries.

    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
     both
    -3.70
    Both
    -2.56
     Both
    -2.38
     BOTH
    -1.76
    ทั้ง
    -1.76
     ambos
    -1.66
     ambas
    -1.59
    both
    -1.56
     beide
    -1.52
     zowel
    -1.46
    POSITIVE LOGITS
     alcuni
    1.31
     alcune
    1.30
     languid
    1.23
     myriad
    1.23
    での
    1.21
     pivotal
    1.20
     superstar
    1.19
     deliciously
    1.16
     unn
    1.16
     magnific
    1.15
    Activations Density 0.020%

    No Known Activations