© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 15910
    Prev
    Next
    INDEX
    Explanations

    tears and emotional reactions

    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_40_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
     Cable
    0.43
     सीएच
    0.39
    olica
    0.39
    cable
    0.39
     Magnet
    0.38
    [multimodal]
    0.38
     PI
    0.37
    Trich
    0.37
     Madden
    0.36
     Warehouse
    0.36
    POSITIVE LOGITS
     tears
    2.45
     Tears
    2.20
    涙
    1.98
     wept
    1.84
     lágrimas
    1.81
    泣
    1.73
     weeping
    1.73
    泪
    1.73
     tear
    1.72
     weep
    1.67
    Activations Density 0.045%

    No Known Activations