© 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. 130257
    Prev
    Next
    INDEX
    Explanations

    religious and political terms

    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
    ccco
    0.44
    Ყ
    0.43
    格外
    0.43
    鼍
    0.41
    ícím
    0.41
    阊
    0.41
     $:=$
    0.41
    તુ
    0.40
    ണ്യ
    0.40
    Favourites
    0.40
    POSITIVE LOGITS
     continue
    0.46
     symbolic
    0.44
     symbolism
    0.42
     hailed
    0.42
     steel
    0.42
     pokrač
    0.40
     continuation
    0.40
     judiciary
    0.40
     continuar
    0.39
     weiterhin
    0.38
    Activations Density 0.001%

    No Known Activations