© 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. 43372
    Prev
    Next
    INDEX
    Explanations

    complement words

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

    The neuron is triggered by tokens beginning with the character sequence “comple” (as in complex, complete, complementary, complementation, etc.).

    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
    '
    -3.47
     ‘‘
    -2.73
    亹
    -2.56
    蛏
    -2.47
    🡺
    -2.33
     формы
    -2.30
    ↵↵
    -2.28
     acredita
    -2.20
    CHREIB
    -2.20
     ‘’
    -2.17
    POSITIVE LOGITS
    al
    3.03
    These
    2.95
    er
    2.94
    e
    2.58
    This
    2.48
    棪
    2.45
     Because
    2.45
    ſtra
    2.41
    軼
    2.41
    لينا
    2.36
    Activations Density 0.005%

    No Known Activations