© 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. 22-GEMMASCOPE-RES-131K
    7. 15226
    Prev
    Next
    INDEX
    Explanations

    your or you

    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_22/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
     Khart
    -1.38
     カット
    -1.24
    .
    -1.23
     ofrecemos
    -1.23
     skool
    -1.22
     richieste
    -1.22
     Gara
    -1.19
    かわらず
    -1.16
     Futsal
    -1.16
     glabrous
    -1.16
    POSITIVE LOGITS
     your
    2.88
     you
    2.63
    Kalau
    1.59
     Pastikan
    1.59
    ığınız
    1.57
    dengan
    1.56
    sebagai
    1.55
     подрост
    1.55
    You
    1.49
     YOU
    1.49
    Activations Density 0.004%

    No Known Activations