© 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. 103736
    Prev
    Next
    INDEX
    Explanations

    noble contexts

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

    The neuron activates whenever it encounters the adjective “noble” (as in noble work, noble family, noble gases, etc.).

    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
     unſ
    -2.48
    谖
    -2.45
    sudadera
    -2.44
     jejich
    -2.38
     REALLY
    -2.38
    柺
    -2.28
     nových
    -2.28
    掼
    -2.25
    
    -2.20
    jaqueta
    -2.19
    POSITIVE LOGITS
    }$
    2.88
    ;
    2.77
     During
    2.22
    2.09
     alberi
    2.05
    而
    2.05
    های
    2.03
     While
    2.03
     atau
    1.99
    或
    1.97
    Activations Density 0.001%
    No Known Activations