© 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. 15455
    Prev
    Next
    INDEX
    Explanations

    types and reactions

    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
     yıllık
    1.29
    <unused654>
    1.23
     millones
    1.22
     ambit
    1.22
    嶈
    1.21
     distributions
    1.18
     rapports
    1.18
     Instr
    1.17
    দিগের
    1.17
     spanning
    1.17
    POSITIVE LOGITS
    co
    0.98
    est
    0.91
    äser
    0.89
    ظ
    0.88
    seen
    0.87
     ظ
    0.87
    =(\
    0.85
    ்ய
    0.84
    re
    0.84
    ضة
    0.83
    Activations Density 0.006%

    No Known Activations