© 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. 71852
    Prev
    Next
    INDEX
    Explanations

    control and its contexts

    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
    '
    -1.87
     '
    -1.63
    身后的
    -1.58
     preservar
    -1.41
    -1.37
     to
    -1.36
    ⌀
    -1.33
     CRIME
    -1.30
     naturais
    -1.27
    ซ์
    -1.27
    POSITIVE LOGITS
     control
    2.08
     Control
    1.72
    さてさて
    1.54
    ではでは
    1.53
     télécommande
    1.48
     از
    1.46
    {
    1.45
    潾
    1.45
    规定
    1.41
    ING
    1.39
    Activations Density 0.068%

    No Known Activations