© 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. 10-GEMMASCOPE-RES-131K
    7. 42227
    Prev
    Next
    INDEX
    Explanations

    waters off or near

    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
     parachoque
    -3.13
    鲧
    -2.86
    litude
    -2.67
    揼
    -2.58
    ⬈
    -2.55
     aislados
    -2.55
    抬手
    -2.52
    
    -2.50
    𓆏
    -2.45
    肏
    -2.44
    POSITIVE LOGITS
    to
    3.13
     Then
    2.91
    但我
    2.86
    [
    2.83
    {
    2.81
    (
    2.75
    m
    2.64
    //
    2.64
    d
    2.61
    л
    2.58
    Activations Density 0.005%

    No Known Activations