© 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. 86548
    Prev
    Next
    INDEX
    Explanations

    master and slave relationships

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

    This neuron spotlights mentions of "slave" (as in a slave device or slave role).

    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
     gewiß
    -1.84
    餮
    -1.66
     remained
    -1.62
     vicina
    -1.57
     męska
    -1.53
    istocene
    -1.53
     alrededores
    -1.49
    儅
    -1.48
    ('');
    -1.45
    .
    -1.44
    POSITIVE LOGITS
    м
    1.80
    the
    1.78
    us
    1.75
    nitř
    1.70
    with
    1.70
     pendapat
    1.69
    izes
    1.68
    where
    1.66
     rất
    1.66
    on
    1.63
    Activations Density 0.016%

    No Known Activations