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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84803
    Prev
    Next
    INDEX
    Explanations

    EventArgs in C# 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
     или
    -2.38
    т
    -2.31
    й
    -2.16
     deutscher
    -2.13
     یا
    -2.11
    ."
    -1.99
     she
    -1.95
    箝
    -1.92
    März
    -1.90
    ㉗
    -1.90
    POSITIVE LOGITS
    ?”
    2.69
     Consejos
    2.38
     “
    2.34
    ar
    2.16
    哢
    2.13
    …”
    2.03
     …”
    2.02
    EventArgs
    1.93
    .
    1.90
     verdaderamente
    1.86
    Activations Density 0.001%

    No Known Activations