© 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. 50415
    Prev
    Next
    INDEX
    Explanations

    Chinese and English queries

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

    This neuron detects programming‐language code, especially import statements and other code‐structure lines.

    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
     if
    -0.89
     注册
    -0.78
     considera
    -0.78
     cerrado
    -0.77
     four
    -0.77
     createUser
    -0.77
     fábrica
    -0.77
    tuuri
    -0.77
     this
    -0.76
    chino
    -0.76
    POSITIVE LOGITS
     query
    1.81
    查询
    1.73
    query
    1.58
    qry
    1.48
     QUERY
    1.36
    Query
    1.24
     查询
    1.15
    查詢
    1.12
     Query
    1.09
    QUERY
    1.09
    Activations Density 0.004%

    No Known Activations