© 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. 166743
    Prev
    Next
    INDEX
    Explanations

    purpose or time

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

    while lacking or often get

    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
     ব্লগ
    0.52
     بە
    0.52
     belirli
    0.51
     Dương
    0.50
     chịu
    0.49
     ബ
    0.48
     কতকগুলি
    0.48
     lượng
    0.48
     maint
    0.48
     estuv
    0.47
    POSITIVE LOGITS
    or
    0.47
    喤
    0.43
    el
    0.43
    रीन
    0.42
    re
    0.42
    리로
    0.42
    er
    0.41
    ations
    0.41
    Ref
    0.40
    ন
    0.40
    Activations Density 0.000%

    No Known Activations