© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93189
    Prev
    Next
    INDEX
    Explanations

    export-oriented

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

    The neuron is activated by occurrences of the trade or data transfer verbs “export” and “import” (and their derivatives).

    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
     iconos
    -0.95
    ᑕ
    -0.93
    ativität
    -0.89
    넓
    -0.88
    Ｑ
    -0.86
    Recep
    -0.85
    ازات
    -0.85
    ustos
    -0.84
    ディダス
    -0.82
     зовні
    -0.82
    POSITIVE LOGITS
     oriented
    1.05
    oriented
    1.02
     of
    0.97
    挫
    0.93
    orient
    0.93
     Oriented
    0.93
     orient
    0.90
    пуск
    0.80
    向き
    0.79
     orientation
    0.77
    Activations Density 0.016%

    No Known Activations