© 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. 192261
    Prev
    Next
    INDEX
    Explanations

    Chinese literary forms and features

    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
    כּ
    0.52
     કંપની
    0.44
     शुर
    0.44
    睄
    0.44
    运营
    0.43
    कौन
    0.43
     Tecnología
    0.43
     департа
    0.43
     tecnologías
    0.43
     पिक
    0.43
    POSITIVE LOGITS
     folk
    0.50
     archaeological
    0.46
     Folk
    0.44
     versions
    0.42
    《
    0.42
     crit
    0.42
     medieval
    0.41
     archaeology
    0.40
     nghiệm
    0.39
    versions
    0.39
    Activations Density 0.007%

    No Known Activations