© 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. 129035
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to words and phrases about reciprocation—giving back, rewards, thanks, or mutual exchange.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    loyalty and recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    dicionado
    -0.83
     grammes
    -0.81
     estampa
    -0.81
    lossenen
    -0.79
    лове
    -0.79
    áreas
    -0.79
     絵
    -0.78
     spazio
    -0.78
    ティン
    -0.77
    ációs
    -0.77
    POSITIVE LOGITS
     who
    1.47
     deserve
    1.19
     remercier
    1.07
     whom
    1.01
     sacrifices
    0.95
     contributed
    0.94
     Ведь
    0.94
     deserves
    0.92
     support
    0.89
     sayesinde
    0.89
    Activations Density 0.030%

    No Known Activations