© 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. 22-GEMMASCOPE-RES-131K
    7. 84032
    Prev
    Next
    INDEX
    Explanations

    technical control and sequencing

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

    The neuron strongly activates on content-bearing technical terms—e.g. specialized nouns, variable names, and jargon—in code, scientific, and technical prose.

    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
     prostitu
    -1.26
     plastique
    -1.24
     maso
    -1.09
     kado
    -1.06
     medie
    -1.05
     pompa
    -1.05
     tma
    -1.05
     savon
    -1.05
     parf
    -1.04
     trist
    -1.04
    POSITIVE LOGITS
     and
    1.24
     llega
    1.00
    asantry
    0.98
     lecciones
    0.98
    estä
    0.97
     también
    0.95
    flashdata
    0.94
     și
    0.94
     fueron
    0.92
     encuentra
    0.91
    Activations Density 0.027%

    No Known Activations