© 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. 83075
    Prev
    Next
    INDEX
    Explanations

    programming, upload, backup, send

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

    This neuron detects non-Latin (CJK) text segments, i.e. Chinese or Japanese words.

    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
    為に
    -1.05
    縻
    -1.02
    helps
    -1.00
     dacă
    -1.00
    的特点
    -0.99
     COMING
    -0.92
    înt
    -0.90
    fes
    -0.90
    came
    -0.90
    within
    -0.89
    POSITIVE LOGITS
    时
    4.16
     when
    4.06
    時
    3.77
    的时候
    3.56
    的時候
    2.61
    时候
    2.58
    when
    2.45
     time
    2.45
    时的
    2.38
     cuando
    2.36
    Activations Density 0.008%

    No Known Activations