© 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. 56799
    Prev
    Next
    INDEX
    Explanations

    verbs of action or state

    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
    Not in Any Lists

    No Comments

    Negative Logits
     имели
    0.46
    探
    0.42
    Bookmarks
    0.41
     měli
    0.39
    Clique
    0.38
    ž
    0.38
     وقلنا
    0.38
    த்து
    0.38
    OMI
    0.37
    评
    0.37
    POSITIVE LOGITS
     любит
    0.52
     himself
    0.52
     pracuje
    0.52
     хочет
    0.50
    жает
    0.49
    ítja
    0.49
    щает
    0.48
    носит
    0.46
    ುತ್ತದೆ
    0.46
     reçoit
    0.45
    Activations Density 0.003%

    No Known Activations