© 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. 10-GEMMASCOPE-RES-131K
    7. 130941
    Prev
    Next
    INDEX
    Explanations

    inside or within location

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

    The neuron fires strongly on non‐Latin (especially Chinese/Japanese) character tokens, i.e. it flags CJK script segments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    .
    -2.81
     笔画
    -2.67
    ly
    -2.34
    釓
    -2.28
    лізу
    -2.28
     Preisen
    -2.23
     皮肤
    -2.17
     ๆ
    -2.16
     recibiendo
    -2.16
    灃
    -2.14
    POSITIVE LOGITS
    這一
    3.00
    是非常
    2.69
    6
    2.61
    9
    2.59
    遢
    2.58
     stellte
    2.52
    是很
    2.52
    3
    2.50
    5
    2.42
     nessuno
    2.36
    Activations Density 0.001%

    No Known Activations