© 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. 111175
    Prev
    Next
    INDEX
    Explanations

    expressing desire or need

    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
    ва
    -2.73
    -
    -2.59
     …
    -2.56
    _
    -2.44
    登上
    -2.44
     của
    -2.44
    ‐
    -2.34
     ‎
    -2.33
    la
    -2.30
    –
    -2.30
    POSITIVE LOGITS
     of
    3.42
    
    2.78
     折り
    2.64
     Hift
    2.52
    ()){
    2.47
     放題
    2.44
     Hinblick
    2.42
    hoben
    2.39
     Главная
    2.31
    夘
    2.31
    Activations Density 0.081%

    No Known Activations