© 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. 215626
    Prev
    Next
    INDEX
    Explanations

    specialised items or descriptions

    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
     Camp
    0.43
    Glenn
    0.39
     apert
    0.39
     pudo
    0.38
     Aiden
    0.38
     Thompson
    0.38
    ith
    0.38
    ena
    0.38
    ᱐
    0.38
    chunk
    0.37
    POSITIVE LOGITS
     specialised
    0.41
     devastating
    0.38
     Specialized
    0.38
     specialized
    0.38
     trailing
    0.37
    স্টার
    0.37
     miễn
    0.36
     commonwealth
    0.36
     निसाब
    0.35
     ഷ
    0.35
    Activations Density 0.001%

    No Known Activations