© 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. 34-GEMMASCOPE-RES-131K
    7. 57092
    Prev
    Next
    INDEX
    Explanations

    direct address with "you" or "ya"

    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_34/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
     jouw
    -0.88
    注明
    -0.82
     Ihrer
    -0.81
     continuará
    -0.79
    讪
    -0.78
    Lindo
    -0.77
     Perché
    -0.77
     む
    -0.76
     rind
    -0.76
     motherfucker
    -0.76
    POSITIVE LOGITS
     ya
    4.97
    Ya
    3.16
     Ya
    3.14
    ya
    2.72
     YA
    2.45
     yah
    2.23
    YA
    2.13
     you
    2.06
     já
    1.95
     yaa
    1.54
    Activations Density 0.028%

    No Known Activations