© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14211
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    t
    0.62
     uncertainty
    0.57
     seemingly
    0.57
    ו
    0.56
    ing
    0.54
     difficulty
    0.54
     merk
    0.53
     fish
    0.52
     change
    0.52
     impetus
    0.51
    POSITIVE LOGITS
     které
    0.76
    ENGLISH
    0.75
     التالية
    0.72
     "@{
    0.69
    下記の
    0.69
    𝘻
    0.69
    வடிக்க
    0.69
    ⓝ
    0.69
    ibase
    0.68
     whiche
    0.68
    Activations Density 0.069%

    No Known Activations