© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30737
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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_16_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
    ير
    0.74
    он
    0.67
    AY
    0.62
    рен
    0.61
    י
    0.60
    عى
    0.59
    ор
    0.58
    ЗИ
    0.57
    бе
    0.57
    aa
    0.57
    POSITIVE LOGITS
    }"
    0.73
     casser
    0.71
     interspersed
    0.68
     inhibitor
    0.66
     irritability
    0.64
     erasing
    0.63
    स
    0.63
     effluent
    0.63
     oligodendrocyte
    0.62
     occurrences
    0.61
    Activations Density 0.001%

    No Known Activations