© 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. 41-GEMMASCOPE-2-RES-262K
    7. 103502
    Prev
    Next
    INDEX
    Explanations

    list items and formatting

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Kauff
    0.41
     epit
    0.40
    |<
    0.39
    বিক
    0.38
     Epit
    0.37
     lace
    0.37
     Dip
    0.37
     Engl
    0.37
     Decker
    0.37
    梧
    0.37
    POSITIVE LOGITS
     温度
    0.45
    ᵉ
    0.44
    isma
    0.43
     variado
    0.42
    खोरी
    0.42
     tratamento
    0.41
     சூழ
    0.40
     तापमान
    0.40
     лечение
    0.39
    醣
    0.39
    Activations Density 0.039%

    No Known Activations