© 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. 103657
    Prev
    Next
    INDEX
    Explanations

    performance contexts

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

    This neuron is specifically activating on the word “performance.”

    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
     predominantly
    -1.20
     производится
    -1.18
     incredibly
    -1.09
     verdaderamente
    -1.05
     hoàn
    -1.05
     temprana
    -1.03
     través
    -1.02
     impoverished
    -0.98
     \"
    -0.98
     extremadamente
    -0.98
    POSITIVE LOGITS
     možno
    1.06
     terakhir
    1.04
     Luar
    1.03
     Budaya
    1.02
    lhe
    1.00
     PÉ
    0.97
    등학교
    0.96
    　　【
    0.95
    ίνει
    0.94
    　　-
    0.94
    Activations Density 0.055%

    No Known Activations