© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66282
    Prev
    Next
    INDEX
    Explanations

    children's lives and futures

    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
     in
    -1.88
    ньому
    -1.87
    )=>{
    
    -1.77
    蜒
    -1.52
    ."
    -1.49
    왓
    -1.45
    𝘨
    -1.45
     finds
    -1.42
    ",
    -1.37
    .'
    -1.37
    POSITIVE LOGITS
     будущего
    1.86
    ㎉
    1.64
     Eſ
    1.57
     aktiviert
    1.56
    carteles
    1.52
    なかなか
    1.47
    觏
    1.42
    ﹍﹍
    1.41
    幾天
    1.40
                              
    1.39
    Activations Density 0.015%

    No Known Activations