© 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. 10-GEMMASCOPE-RES-131K
    7. 99113
    Prev
    Next
    INDEX
    Explanations

    gracious advocate, cordi expanses

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

    The neuron fires on polite, courteous expressions of kindness or gratitude.

    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
    </strong>
    -3.17
     registró
    -2.55
    ть
    -2.45
     pelaksanaan
    -2.25
     aprobó
    -2.22
     It
    -2.22
     Feel
    -2.13
     Lots
    -2.13
     dasarnya
    -2.11
     criticize
    -2.09
    POSITIVE LOGITS
    蔸
    2.36
    猡
    2.22
     wie
    2.08
    ⸫
    1.99
    ﱠ
    1.99
    ﹶ
    1.98
     vea
    1.97
     クー
    1.92
    
    1.92
     taza
    1.91
    Activations Density 0.001%

    No Known Activations