© 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. 137783
    Prev
    Next
    INDEX
    Explanations

    AI, planet, people, mesh, cookie

    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
     Malayalam
    0.43
     VESSELS
    0.39
    বঙ্গের
    0.39
     neurons
    0.38
    ogyakarta
    0.38
    ដឹក
    0.38
     shipwreck
    0.38
     contrary
    0.38
    duration
    0.38
    圩
    0.38
    POSITIVE LOGITS
     Cookie
    0.43
     cookie
    0.41
     shiny
    0.41
     people
    0.39
     reali
    0.39
     rab
    0.38
     사람들이
    0.38
     erw
    0.37
    衷
    0.37
    ண்டி
    0.37
    Activations Density 0.000%

    No Known Activations