© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63147
    Prev
    Next
    INDEX
    Explanations

    dealing with elimination

    np_acts-logits-general · gemini-2.5-flash-lite

    slaughtered much younger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    reaction
    0.47
     t
    0.47
    迪
    0.47
    竭
    0.46
     reaction
    0.45
    攀
    0.45
    い
    0.44
    道
    0.44
    越來越
    0.44
    f
    0.42
    POSITIVE LOGITS
     obtus
    0.53
     başlayalım
    0.52
    )-\
    0.50
     Archive
    0.46
     bandes
    0.46
     déprimées
    0.45
    ición
    0.45
     deles
    0.45
    ğine
    0.45
     halus
    0.45
    Activations Density 0.000%

    No Known Activations