© 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. 10420
    Prev
    Next
    INDEX
    Explanations

    Bahamas

    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
     vacacionales
    -1.91
     alrededores
    -1.86
     různých
    -1.82
    襌
    -1.80
     ſou
    -1.76
     lidí
    -1.75
     понял
    -1.72
    谖
    -1.71
     potřeb
    -1.70
    
    -1.66
    POSITIVE LOGITS
    </h5>
    2.36
    </b>
    1.97
    </td>
    1.90
    </em>
    1.85
    For
    1.66
    Only
    1.56
                
    1.49
    It
    1.46
    They
    1.40
    Our
    1.40
    Activations Density 0.003%

    No Known Activations