© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86566
    Prev
    Next
    INDEX
    Explanations

    imported items

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

    The neuron specifically activates on occurrences of the word “imported.”

    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
    \
    -2.50
    “
    -2.38
     atau
    -2.17
     为
    -2.16
    騷
    -2.13
     många
    -2.11
    许久
    -2.11
     его
    -2.11
    ations
    -2.09
    咘
    -2.09
    POSITIVE LOGITS
    玙
    2.42
    翾
    2.34
     オン
    2.34
    莚
    2.28
    姈
    2.27
    酲
    2.20
    囿
    2.19
    驩
    2.16
    atser
    2.13
    盦
    2.13
    Activations Density 0.011%

    No Known Activations