© 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. 100684
    Prev
    Next
    INDEX
    Explanations

    deportation. deport. them

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

    The neuron strongly activates on words containing the root “port,” especially forms of “deport” (e.g. deports, deported, deportation).

    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
    "
    -3.59
    iv
    -2.45
     это
    -2.41
     eer
    -2.39
    );\
    -2.34
    是他
    -2.33
     моя
    -2.31
    as
    -2.31
     fateful
    -2.31
    分明
    -2.27
    POSITIVE LOGITS
    婓
    2.67
    ↵
    2.59
    焿
    2.55
    殽
    2.44
    "},
    2.44
    ꯷
    2.36
    ちゃんは
    2.31
     كبيرة
    2.31
    保育園
    2.23
    ”，
    2.20
    Activations Density 0.001%

    No Known Activations