© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48160
    Prev
    Next
    INDEX
    Explanations

    damn

    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
     with
    -1.66
     when
    -1.45
    훨
    -1.31
    。"
    -1.27
    !"
    -1.26
     ensuring
    -1.25
    嫫
    -1.24
     سایر
    -1.23
     or
    -1.23
     effectively
    -1.21
    POSITIVE LOGITS
    ),
    1.67
    fusions
    1.29
    {
    1.28
    曏
    1.28
     типов
    1.26
     gummy
    1.23
     ",";
    1.23
    iphery
    1.23
     начинается
    1.23
     damn
    1.22
    Activations Density 0.024%

    No Known Activations