© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7656
    Prev
    Next
    INDEX
    Explanations

    formal and archaic language

    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_22_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
    ตัวเอง
    1.07
     بشكل
    1.07
    한테
    1.05
    줬
    0.99
     পুরোপুরি
    0.97
     emotionally
    0.96
     거죠
    0.95
    တွေ
    0.94
    꿨
    0.94
    doesn
    0.94
    POSITIVE LOGITS
     shall
    1.55
     doth
    1.52
     Upon
    1.51
     verily
    1.50
     unto
    1.46
     hath
    1.46
     upon
    1.43
     thy
    1.40
     herein
    1.37
    Upon
    1.36
    Activations Density 0.181%

    No Known Activations