© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2133
    Prev
    Next
    INDEX
    Explanations

    configure or setup

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

    The neuron fires strongly on occurrences of personal pronouns—especially “I” and “you”—in these Q&A posts.

    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
    UpdateDate
    -0.97
     motoru
    -0.97
     proposé
    -0.97
     држа
    -0.96
     pensato
    -0.92
    ApiRequest
    -0.91
    materi
    -0.91
    خيص
    -0.87
    umentar
    -0.87
    TAINS
    -0.86
    POSITIVE LOGITS
     setup
    2.72
     configure
    2.38
     configured
    2.23
     configuring
    2.20
     define
    2.06
    設定
    2.06
    configure
    2.06
    setup
    2.05
    配置
    2.00
     set
    1.90
    Activations Density 0.325%

    No Known Activations