© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54313
    Prev
    Next
    INDEX
    Explanations

    cup, throat, house, ware, reinforced

    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_22/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
    incontro
    -0.94
    جمعیت
    -0.94
    icona
    -0.93
     oczy
    -0.92
     reputable
    -0.91
    そうな
    -0.88
    ươ
    -0.88
     ibunya
    -0.88
     вироб
    -0.87
    Тру
    -0.87
    POSITIVE LOGITS
    utación
    1.16
    ulario
    1.12
    ˟
    1.12
    szak
    1.12
    ServletConfig
    1.10
    &+
    1.09
     especialmente
    1.07
    $
    1.05
     spesielt
    1.05
    льность
    1.04
    Activations Density 0.048%

    No Known Activations