© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56851
    Prev
    Next
    INDEX
    Explanations

    expressing agreement

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

    The neuron strongly activates on explicit expressions of agreement (e.g. “agree”) and related intensifiers conveying concurrence.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     meaningful
    -0.97
    自身的
    -0.97
     credible
    -0.95
     advertencia
    -0.94
    }}=$
    -0.94
    ()">
    -0.93
    ítimo
    -0.92
    %">
    -0.92
     >
    -0.92
    }>
    -0.91
    POSITIVE LOGITS
     wholeheartedly
    2.11
     agree
    1.87
    Agree
    1.55
     agrees
    1.54
     полностью
    1.52
    agree
    1.48
     completely
    1.44
     Agree
    1.43
     that
    1.41
     totally
    1.38
    Activations Density 0.009%

    No Known Activations