© 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. 220095
    Prev
    Next
    INDEX
    Explanations

    morbidity or not careful

    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
    രം
    0.41
    谟
    0.38
    ват
    0.36
    ାର
    0.36
    harmon
    0.35
    Vorlage
    0.34
    owania
    0.34
     quis
    0.34
     biber
    0.34
    
    0.34
    POSITIVE LOGITS
    configs
    0.43
     ambush
    0.42
     dijual
    0.42
     ശ
    0.39
     morbidity
    0.39
    acon
    0.38
     sorry
    0.38
     sh
    0.38
     morbid
    0.38
    નું
    0.37
    Activations Density 0.000%

    No Known Activations