© 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. 71843
    Prev
    Next
    INDEX
    Explanations

    first off, first up, first though

    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
     
    -2.03
    "},
    -1.99
     any
    -1.73
    in
    -1.72
    ):
    -1.60
    </th>
    -1.59
    </
    -1.58
    )",
    -1.57
    </h1>
    -1.56
    {
    -1.55
    POSITIVE LOGITS
     设备
    2.13
     办
    1.97
    
    1.96
    
    1.96
    ⎆
    1.94
    使用方法
    1.94
     braw
    1.91
    轳
    1.91
    
    1.86
    最重要的
    1.85
    Activations Density 0.002%

    No Known Activations