© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80203
    Prev
    Next
    INDEX
    Explanations

    sitting position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    坐
    0.72
     sit
    0.71
     duduk
    0.70
     sitting
    0.69
    Sit
    0.66
    sitting
    0.64
     Sit
    0.64
    Sitting
    0.64
     sits
    0.62
     seated
    0.62
    POSITIVE LOGITS
     wandering
    0.35
    रीबन
    0.35
     wanders
    0.35
    ່າງ
    0.34
    raje
    0.34
    娉
    0.34
    笄
    0.33
     walking
    0.33
     helper
    0.33
    ඃ
    0.33
    Activations Density 0.006%

    No Known Activations