© 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. 60185
    Prev
    Next
    INDEX
    Explanations

    top-down and bottom-up

    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
     nawet
    -2.16
     навіть
    -1.79
    夸张
    -1.78
     penghar
    -1.73
    -1.73
    ectady
    -1.72
    伫
    -1.71
     групи
    -1.64
     resides
    -1.62
    "};
    -1.60
    POSITIVE LOGITS
    歼
    1.98
    liegenden
    1.98
    ᯾
    1.88
     personalización
    1.80
     successes
    1.73
     engender
    1.72
     fabricación
    1.71
    ㉕
    1.71
    諴
    1.70
    介入
    1.70
    Activations Density 0.005%

    No Known Activations