© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 63596
    Prev
    Next
    INDEX
    Explanations

    being or variations of "to be"

    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_41_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
    殷
    0.39
    йдет
    0.38
     Тере
    0.38
     rigs
    0.37
    ItemList
    0.36
    XPATH
    0.36
     Wicked
    0.36
    йдёт
    0.36
     {.
    0.36
     ত্রিশ
    0.35
    POSITIVE LOGITS
     Being
    1.61
    Being
    1.61
     BEING
    1.52
     being
    1.50
    being
    1.45
     быть
    1.26
     sendo
    1.26
     होने
    1.24
     siendo
    1.24
     essere
    1.13
    Activations Density 0.126%

    No Known Activations