© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98783
    Prev
    Next
    INDEX
    Explanations

    query keywords and programming imports

    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
    Negative Logits
     -
    -2.28
    with
    -2.19
     мы
    -1.95
    }$,
    -1.95
     =
    -1.90
    ⼠
    -1.84
     berühmten
    -1.81
     Mischung
    -1.80
    s
    -1.76
    3
    -1.75
    POSITIVE LOGITS
    鼱
    1.90
    嗞
    1.89
    螄
    1.85
    ほうが
    1.83
    以上です
    1.83
     رت
    1.82
     vergeten
    1.78
    ,
    1.75
    わけで
    1.71
    
    1.68
    Activations Density 0.028%

    No Known Activations