© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13986
    Prev
    Next
    INDEX
    Explanations

    introductions and explanations

    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_40_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
    provides
    0.23
    р
    0.22
     streamlines
    0.21
     ensures
    0.21
    ಙ
    0.21
     শ্
    0.21
    从而
    0.21
     এইরূপে
    0.21
    ר
    0.21
    डून
    0.20
    POSITIVE LOGITS
     Instead
    0.40
     Literally
    0.33
     Actually
    0.30
    Instead
    0.30
     Firstly
    0.29
     Luckily
    0.29
     Итак
    0.29
     Namely
    0.29
     Incidentally
    0.29
     Thankfully
    0.29
    Activations Density 0.005%

    No Known Activations