© 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. 13718
    Prev
    Next
    INDEX
    Explanations

    Chevrolet and Chevy vehicles

    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
    ITHUB
    -2.03
    ❉
    -1.97
    </h4>
    -1.95
     dragón
    -1.94
    hline
    -1.93
    .”
    -1.91
     
    -1.89
    section
    -1.89
    ならず
    -1.89
    栴
    -1.85
    POSITIVE LOGITS
    2
    2.50
    もある
    2.31
    5
    2.17
     gearbeitet
    2.11
     erklär
    2.06
    ers
    2.05
    うちの
    1.98
    绀
    1.96
    Chevrolet
    1.92
    dientemente
    1.91
    Activations Density 0.001%

    No Known Activations