© 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. 1327
    Prev
    Next
    INDEX
    Explanations

    sql comments and code

    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
     what
    -1.81
     Gebühren
    -1.36
     dificultad
    -1.34
     wiesz
    -1.30
     today
    -1.26
     dalej
    -1.25
     Gerät
    -1.23
     zainteres
    -1.23
     muchísimo
    -1.22
     prochain
    -1.21
    POSITIVE LOGITS
    这是一
    1.45
    OOTDTY
    1.42
    咘
    1.41
     visse
    1.38
    /*++
    1.30
    //-----
    1.29
    //};
    1.29
    //----
    1.27
    !");
    1.24
    瞜
    1.23
    Activations Density 0.082%

    No Known Activations