© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26047
    Prev
    Next
    INDEX
    Explanations

    sit down, sit home

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ر
    0.66
    ל
    0.62
    ي
    0.60
    ascular
    0.57
    Бы
    0.56
    К
    0.52
    SI
    0.52
    Continu
    0.52
    baren
    0.52
     uncomment
    0.52
    POSITIVE LOGITS
     앉
    0.93
     duduk
    0.90
     sitzt
    0.88
     ngồi
    0.87
     sit
    0.82
     sitting
    0.79
    坐
    0.79
    앉
    0.79
     Sit
    0.79
     बैठकर
    0.76
    Activations Density 0.061%

    No Known Activations