© 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. 207298
    Prev
    Next
    INDEX
    Explanations

    Broncos, Delta, messages, granted, residents, able, not, adopt

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

    brave discovery purpose definitely chain

    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
     giảng
    0.53
     erforderlich
    0.52
     lucro
    0.52
     miliardi
    0.51
     জন্মগ্রহণ
    0.48
     combinatie
    0.48
     combina
    0.48
    뭡
    0.47
     miljoen
    0.46
     rekao
    0.46
    POSITIVE LOGITS
    aft
    0.46
    IUS
    0.46
    ius
    0.46
    fic
    0.46
     unity
    0.45
    osk
    0.44
    kj
    0.44
    一颗
    0.44
    ts
    0.43
    شک
    0.43
    Activations Density 0.000%

    No Known Activations