© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192210
    Prev
    Next
    INDEX
    Explanations

    specific topics and their context

    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
    Negative Logits
     arsenal
    0.42
    をもって
    0.40
    氻
    0.39
     Zero
    0.39
     Commandant
    0.39
     შეი
    0.38
     Morgan
    0.38
     Hiro
    0.38
     Roberts
    0.38
     Rounds
    0.37
    POSITIVE LOGITS
    guien
    0.45
    琉
    0.42
    的事情
    0.42
    rbrakk
    0.39
    ውነ
    0.38
    Blockchain
    0.38
    কান
    0.37
    (">
    0.37
    摩
    0.36
    紹介
    0.36
    Activations Density 2.412%

    No Known Activations