© 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. 100447
    Prev
    Next
    INDEX
    Explanations

    to continue to do something

    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
    鲣
    -1.88
     trovano
    -1.87
    贽
    -1.86
    ！！！！
    -1.70
     Irán
    -1.66
    ֢
    -1.65
    鯷
    -1.64
    
    -1.63
    还真
    -1.63
     手作り
    -1.63
    POSITIVE LOGITS
     who
    2.08
    ",
    2.05
    ”
    2.02
     другие
    1.80
    訁
    1.77
    the
    1.75
    '
    1.68
     และ
    1.68
    ”,
    1.66
    who
    1.61
    Activations Density 0.013%

    No Known Activations