© 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. 31-GEMMASCOPE-2-RES-262K
    7. 30730
    Prev
    Next
    INDEX
    Explanations

    then conditional

    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_31_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
     =\
    0.39
     られ
    0.39
     glassy
    0.38
     тільки
    0.37
    อย่าง
    0.37
    อย
    0.36
    Only
    0.36
     marvell
    0.36
     منتقل
    0.36
     dozen
    0.36
    POSITIVE LOGITS
    则
    0.51
     তাহলে
    0.50
     then
    0.49
    then
    0.46
     então
    0.44
     thì
    0.43
    แล้ว
    0.43
     entonces
    0.42
     فإن
    0.42
     则
    0.41
    Activations Density 0.033%

    No Known Activations