© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 18787
    Prev
    Next
    INDEX
    Explanations

    sitting and posture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    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
    ToListAsync
    0.34
    ipkan
    0.33
    pegno
    0.32
    toMap
    0.32
    שור
    0.32
     Buffered
    0.32
    Stevens
    0.32
    藜
    0.32
     ステン
    0.31
    HandleFunc
    0.31
    POSITIVE LOGITS
     sitting
    4.03
     sit
    3.92
     Sitting
    3.67
    Sitting
    3.67
    坐
    3.66
    sitting
    3.56
     sits
    3.55
    Sit
    3.53
     Sit
    3.52
     ngồi
    3.38
    Activations Density 0.064%

    No Known Activations