© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119004
    Prev
    Next
    INDEX
    Explanations

    polite and courteous behavior

    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_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>
    -1.66
        
    -1.63
     united
    -1.57
          
    -1.52
    vı
    -1.52
     –
    -1.51
    imerick
    -1.49
    ICULO
    -1.48
     затем
    -1.47
    י
    -1.47
    POSITIVE LOGITS
    7
    2.22
    9
    2.09
    鶿
    1.95
    ;
    1.91
    8
    1.87
    0
    1.86
    5
    1.75
    鷽
    1.73
    1.66
    6
    1.63
    Activations Density 0.014%

    No Known Activations