© 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. 34-GEMMASCOPE-RES-131K
    7. 64922
    Prev
    Next
    INDEX
    Explanations

    Antonio Armijo, Polymer optical

    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_34/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
     hospital
    -0.82
     orientation
    -0.82
    海軍
    -0.73
    breo
    -0.73
     חיי
    -0.71
    ategor
    -0.71
    orientation
    -0.71
    黄
    -0.71
    ooplankton
    -0.71
    segna
    -0.70
    POSITIVE LOGITS
     italic
    0.96
     sepol
    0.84
     обы
    0.84
     подчер
    0.81
    slash
    0.81
    をご覧ください
    0.80
    Рецепт
    0.80
    外部链接
    0.80
    Karol
    0.80
     homicidio
    0.79
    Activations Density 0.002%

    No Known Activations