© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33935
    Prev
    Next
    INDEX
    Explanations

    willingness and agreement

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

    The neuron fires on words and phrases expressing agreement or enthusiastic acceptance (e.g. accept, agree, yes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kän
    -1.05
     only
    -1.01
     впечатление
    -0.96
     prochains
    -0.96
     prossima
    -0.96
    Patience
    -0.94
    breviations
    -0.92
     katun
    -0.88
     during
    -0.88
    katakan
    -0.88
    POSITIVE LOGITS
     agreed
    1.21
     willing
    1.21
     согласи
    1.16
     agree
    1.16
     qualquer
    1.13
     ngay
    1.13
     gladly
    1.13
     readily
    1.05
     agreeable
    1.05
    žad
    1.04
    Activations Density 0.030%

    No Known Activations