© 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. 192898
    Prev
    Next
    INDEX
    Explanations

    optimized, transformed, driven

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

    places followed by 'where'

    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
    帮忙
    0.68
     nějak
    0.66
     arşiv
    0.65
     זה
    0.64
    זה
    0.64
     recop
    0.64
     congrats
    0.64
     😁
    0.63
     این
    0.63
    讨论
    0.63
    POSITIVE LOGITS
    ’
    0.63
     transformed
    0.61
    -,
    0.60
    ·
    0.59
    0.57
    driven
    0.56
     operated
    0.55
    transformed
    0.54
    -
    0.54
     creates
    0.54
    Activations Density 0.001%

    No Known Activations