© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54438
    Prev
    Next
    INDEX
    Explanations

    author et al. year references

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

    This neuron detects author names in academic‐style citations.

    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
     puse
    -1.20
    Aplicación
    -1.01
    Alongside
    -1.00
    竟然是
    -0.97
     conex
    -0.96
     navigu
    -0.95
     capilar
    -0.94
     fà
    -0.92
    Rés
    -0.91
    旁边
    -0.91
    POSITIVE LOGITS
     variés
    1.16
     vitales
    1.14
     ФИ
    1.11
     świąte
    1.10
     zimowa
    1.05
     traditionnels
    1.05
     supérieure
    1.05
     diamètre
    1.04
     chaude
    1.02
     المصدر
    1.01
    Activations Density 0.010%

    No Known Activations